John C. S. Lui

Yu-Zhen Janice Chen, Lin Yang, Xuchuang Wang et al. · uw

This paper studies a cooperative multi-agent multi-armed stochastic bandit problem where agents operate asynchronously -- agent pull times and rates are unknown, irregular, and heterogeneous -- and face the same instance of a K-armed bandit problem. Agents can share reward information to speed up the learning process at additional communication costs. We propose ODC, an on-demand communication protocol that tailors the communication of each pair of agents based on their empirical pull times. ODC is efficient when the pull times of agents are highly heterogeneous, and its communication complexity depends on the empirical pull times of agents. ODC is a generic protocol that can be integrated into most cooperative bandit algorithms without degrading their performance. We then incorporate ODC into the natural extensions of UCB and AAE algorithms and propose two communication-efficient cooperative algorithms. Our analysis shows that both algorithms are near-optimal in regret.

Xutong Liu, Jinhang Zuo, Siwei Wang et al. · uw

In this paper, we study the combinatorial semi-bandits (CMAB) and focus on reducing the dependency of the batch-size $K$ in the regret bound, where $K$ is the total number of arms that can be pulled or triggered in each round. First, for the setting of CMAB with probabilistically triggered arms (CMAB-T), we discover a novel (directional) triggering probability and variance modulated (TPVM) condition that can replace the previously-used smoothness condition for various applications, such as cascading bandits, online network exploration and online influence maximization. Under this new condition, we propose a BCUCB-T algorithm with variance-aware confidence intervals and conduct regret analysis which reduces the $O(K)$ factor to $O(\log K)$ or $O(\log^2 K)$ in the regret bound, significantly improving the regret bounds for the above applications. Second, for the setting of non-triggering CMAB with independent arms, we propose a SESCB algorithm which leverages on the non-triggering version of the TPVM condition and completely removes the dependency on $K$ in the leading regret. As a valuable by-product, the regret analysis used in this paper can improve several existing results by a factor of $O(\log K)$. Finally, experimental evaluations show our superior performance compared with benchmark algorithms in different applications.

Xutong Liu, Jinhang Zuo, Siwei Wang et al. · uw

We study contextual combinatorial bandits with probabilistically triggered arms (C$^2$MAB-T) under a variety of smoothness conditions that capture a wide range of applications, such as contextual cascading bandits and contextual influence maximization bandits. Under the triggering probability modulated (TPM) condition, we devise the C$^2$-UCB-T algorithm and propose a novel analysis that achieves an $\tilde{O}(d\sqrt{KT})$ regret bound, removing a potentially exponentially large factor $O(1/p_{\min})$, where $d$ is the dimension of contexts, $p_{\min}$ is the minimum positive probability that any arm can be triggered, and batch-size $K$ is the maximum number of arms that can be triggered per round. Under the variance modulated (VM) or triggering probability and variance modulated (TPVM) conditions, we propose a new variance-adaptive algorithm VAC$^2$-UCB and derive a regret bound $\tilde{O}(d\sqrt{T})$, which is independent of the batch-size $K$. As a valuable by-product, our analysis technique and variance-adaptive algorithm can be applied to the CMAB-T and C$^2$MAB setting, improving existing results there as well. We also include experiments that demonstrate the improved performance of our algorithms compared with benchmark algorithms on synthetic and real-world datasets.

Zhiyong Wang, Xutong Liu, Shuai Li et al. · uw

Conversational contextual bandits elicit user preferences by occasionally querying for explicit feedback on key-terms to accelerate learning. However, there are aspects of existing approaches which limit their performance. First, information gained from key-term-level conversations and arm-level recommendations is not appropriately incorporated to speed up learning. Second, it is important to ask explorative key-terms to quickly elicit the user's potential interests in various domains to accelerate the convergence of user preference estimation, which has never been considered in existing works. To tackle these issues, we first propose ``ConLinUCB", a general framework for conversational bandits with better information incorporation, combining arm-level and key-term-level feedback to estimate user preference in one step at each time. Based on this framework, we further design two bandit algorithms with explorative key-term selection strategies, ConLinUCB-BS and ConLinUCB-MCR. We prove tighter regret upper bounds of our proposed algorithms. Particularly, ConLinUCB-BS achieves a regret bound of $O(d\sqrt{T\log T})$, better than the previous result $O(d\sqrt{T}\log T)$. Extensive experiments on synthetic and real-world data show significant advantages of our algorithms in learning accuracy (up to 54\% improvement) and computational efficiency (up to 72\% improvement), compared to the classic ConUCB algorithm, showing the potential benefit to recommender systems.

Xutong Liu, Haoru Zhao, Tong Yu et al. · uw

Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems. A line of works, called the clustering of bandits (CLUB), utilize the collaborative effect over users and dramatically improve the recommendation quality. Owing to the increasing application scale and public concerns about privacy, there is a growing demand to keep user data decentralized and push bandit learning to the local server side. Existing CLUB algorithms, however, are designed under the centralized setting where data are available at a central server. We focus on studying the federated online clustering of bandit (FCLUB) problem, which aims to minimize the total regret while satisfying privacy and communication considerations. We design a new phase-based scheme for cluster detection and a novel asynchronous communication protocol for cooperative bandit learning for this problem. To protect users' privacy, previous differential privacy (DP) definitions are not very suitable, and we propose a new DP notion that acts on the user cluster level. We provide rigorous proofs to show that our algorithm simultaneously achieves (clustered) DP, sublinear communication complexity and sublinear regret. Finally, experimental evaluations show our superior performance compared with benchmark algorithms.

Jun He, Laura Balzano, John C. S. Lui

This paper presents GRASTA (Grassmannian Robust Adaptive Subspace Tracking Algorithm), an efficient and robust online algorithm for tracking subspaces from highly incomplete information. The algorithm uses a robust $l^1$-norm cost function in order to estimate and track non-stationary subspaces when the streaming data vectors are corrupted with outliers. We apply GRASTA to the problems of robust matrix completion and real-time separation of background from foreground in video. In this second application, we show that GRASTA performs high-quality separation of moving objects from background at exceptional speeds: In one popular benchmark video example, GRASTA achieves a rate of 57 frames per second, even when run in MATLAB on a personal laptop.

Russell Lee, Bo Sun, Mohammad Hajiesmaili et al.

This paper develops learning-augmented algorithms for energy trading in volatile electricity markets. The basic problem is to sell (or buy) $k$ units of energy for the highest revenue (lowest cost) over uncertain time-varying prices, which can framed as a classic online search problem in the literature of competitive analysis. State-of-the-art algorithms assume no knowledge about future market prices when they make trading decisions in each time slot, and aim for guaranteeing the performance for the worst-case price sequence. In practice, however, predictions about future prices become commonly available by leveraging machine learning. This paper aims to incorporate machine-learned predictions to design competitive algorithms for online search problems. An important property of our algorithms is that they achieve performances competitive with the offline algorithm in hindsight when the predictions are accurate (i.e., consistency) and also provide worst-case guarantees when the predictions are arbitrarily wrong (i.e., robustness). The proposed algorithms achieve the Pareto-optimal trade-off between consistency and robustness, where no other algorithms for online search can improve on the consistency for a given robustness. Further, we extend the basic online search problem to a more general inventory management setting that can capture storage-assisted energy trading in electricity markets. In empirical evaluations using traces from real-world applications, our learning-augmented algorithms improve the average empirical performance compared to benchmark algorithms, while also providing improved worst-case performance.

Xuchuang Wang, Hong Xie, John C. S. Lui

Multi-player multi-armed bandits (MMAB) study how decentralized players cooperatively play the same multi-armed bandit so as to maximize their total cumulative rewards. Existing MMAB models mostly assume when more than one player pulls the same arm, they either have a collision and obtain zero rewards, or have no collision and gain independent rewards, both of which are usually too restrictive in practical scenarios. In this paper, we propose an MMAB with shareable resources as an extension to the collision and non-collision settings. Each shareable arm has finite shareable resources and a "per-load" reward random variable, both of which are unknown to players. The reward from a shareable arm is equal to the "per-load" reward multiplied by the minimum between the number of players pulling the arm and the arm's maximal shareable resources. We consider two types of feedback: sharing demand information (SDI) and sharing demand awareness (SDA), each of which provides different signals of resource sharing. We design the DPE-SDI and SIC-SDA algorithms to address the shareable arm problem under these two cases of feedback respectively and prove that both algorithms have logarithmic regrets that are tight in the number of rounds. We conduct simulations to validate both algorithms' performance and show their utilities in wireless networking and edge computing.

Xuchuang Wang, Hong Xie, John C. S. Lui

We generalize the multiple-play multi-armed bandits (MP-MAB) problem with a shareable arm setting, in which several plays can share the same arm. Furthermore, each shareable arm has a finite reward capacity and a ''per-load'' reward distribution, both of which are unknown to the learner. The reward from a shareable arm is load-dependent, which is the "per-load" reward multiplying either the number of plays pulling the arm, or its reward capacity when the number of plays exceeds the capacity limit. When the "per-load" reward follows a Gaussian distribution, we prove a sample complexity lower bound of learning the capacity from load-dependent rewards and also a regret lower bound of this new MP-MAB problem. We devise a capacity estimator whose sample complexity upper bound matches the lower bound in terms of reward means and capacities. We also propose an online learning algorithm to address the problem and prove its regret upper bound. This regret upper bound's first term is the same as regret lower bound's, and its second and third terms also evidently correspond to lower bound's. Extensive experiments validate our algorithm's performance and also its gain in 5G & 4G base station selection.

Lin Yang, Xuchuang Wang, Mohammad Hajiesmaili et al.

Recently, there has been extensive study of cooperative multi-agent multi-armed bandits where a set of distributed agents cooperatively play the same multi-armed bandit game. The goal is to develop bandit algorithms with the optimal group and individual regrets and low communication between agents. The prior work tackled this problem using two paradigms: leader-follower and fully distributed algorithms. Prior algorithms in both paradigms achieve the optimal group regret. The leader-follower algorithms achieve constant communication costs but fail to achieve optimal individual regrets. The state-of-the-art fully distributed algorithms achieve optimal individual regrets but fail to achieve constant communication costs. This paper presents a simple yet effective communication policy and integrates it into a learning algorithm for cooperative bandits. Our algorithm achieves the best of both paradigms: optimal individual regret and constant communication costs.

Xuchuang Wang, Qingyun Wu, Wei Chen et al.

We study the multi-fidelity multi-armed bandit (MF-MAB), an extension of the canonical multi-armed bandit (MAB) problem. MF-MAB allows each arm to be pulled with different costs (fidelities) and observation accuracy. We study both the best arm identification with fixed confidence (BAI) and the regret minimization objectives. For BAI, we present (a) a cost complexity lower bound, (b) an algorithmic framework with two alternative fidelity selection procedures, and (c) both procedures' cost complexity upper bounds. From both cost complexity bounds of MF-MAB, one can recover the standard sample complexity bounds of the classic (single-fidelity) MAB. For regret minimization of MF-MAB, we propose a new regret definition, prove its problem-independent regret lower bound $Ω(K^{1/3}Λ^{2/3})$ and problem-dependent lower bound $Ω(K\log Λ)$, where $K$ is the number of arms and $Λ$ is the decision budget in terms of cost, and devise an elimination-based algorithm whose worst-cost regret upper bound matches its corresponding lower bound up to some logarithmic terms and, whose problem-dependent bound matches its corresponding lower bound in terms of $Λ$.

Xiaoying Zhang, Junpu Chen, Hongning Wang et al.

Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as search engines, recommender systems, and etc. While the ground-truth logging policy, which generates the logged data, is usually unknown, previous work simply takes its estimated value in off-policy learning, ignoring both high bias and high variance resulted from such an estimator, especially on samples with small and inaccurately estimated logging probabilities. In this work, we explicitly model the uncertainty in the estimated logging policy and propose a Uncertainty-aware Inverse Propensity Score estimator (UIPS) for improved off-policy learning, with a theoretical convergence guarantee. Experiment results on synthetic and three real-world recommendation datasets demonstrate the advantageous sample efficiency of the proposed UIPS estimator against an extensive list of state-of-the-art baselines.

Xiangxiang Dai, Zeyu Zhang, Peng Yang et al. · uw

The rapid evolution of multimedia and computer vision technologies requires adaptive visual model deployment strategies to effectively handle diverse tasks and varying environments. This work introduces AxiomVision, a novel framework that can guarantee accuracy by leveraging edge computing to dynamically select the most efficient visual models for video analytics under diverse scenarios. Utilizing a tiered edge-cloud architecture, AxiomVision enables the deployment of a broad spectrum of visual models, from lightweight to complex DNNs, that can be tailored to specific scenarios while considering camera source impacts. In addition, AxiomVision provides three core innovations: (1) a dynamic visual model selection mechanism utilizing continual online learning, (2) an efficient online method that efficiently takes into account the influence of the camera's perspective, and (3) a topology-driven grouping approach that accelerates the model selection process. With rigorous theoretical guarantees, these advancements provide a scalable and effective solution for visual tasks inherent to multimedia systems, such as object detection, classification, and counting. Empirically, AxiomVision achieves a 25.7\% improvement in accuracy.

Zhiyong Wang, Jize Xie, Xutong Liu et al. · uw

The contextual linear bandit is an important online learning problem where given arm features, a learning agent selects an arm at each round to maximize the cumulative rewards in the long run. A line of works, called the clustering of bandits (CB), utilize the collaborative effect over user preferences and have shown significant improvements over classic linear bandit algorithms. However, existing CB algorithms require well-specified linear user models and can fail when this critical assumption does not hold. Whether robust CB algorithms can be designed for more practical scenarios with misspecified user models remains an open problem. In this paper, we are the first to present the important problem of clustering of bandits with misspecified user models (CBMUM), where the expected rewards in user models can be perturbed away from perfect linear models. We devise two robust CB algorithms, RCLUMB and RSCLUMB (representing the learned clustering structure with dynamic graph and sets, respectively), that can accommodate the inaccurate user preference estimations and erroneous clustering caused by model misspecifications. We prove regret upper bounds of $O(ε_*T\sqrt{md\log T} + d\sqrt{mT}\log T)$ for our algorithms under milder assumptions than previous CB works (notably, we move past a restrictive technical assumption on the distribution of the arms), which match the lower bound asymptotically in $T$ up to logarithmic factors, and also match the state-of-the-art results in several degenerate cases. The techniques in proving the regret caused by misclustering users are quite general and may be of independent interest. Experiments on both synthetic and real-world data show our outperformance over previous algorithms.

Zhi Qi, Hong Xie, Ye Li et al.

This paper proposes LPC-AD, a fast and accurate multivariate time series (MTS) anomaly detection method. LPC-AD is motivated by the ever-increasing needs for fast and accurate MTS anomaly detection methods to support fast troubleshooting in cloud computing, micro-service systems, etc. LPC-AD is fast in the sense that its reduces the training time by as high as 38.2% compared to the state-of-the-art (SOTA) deep learning methods that focus on training speed. LPC-AD is accurate in the sense that it improves the detection accuracy by as high as 18.9% compared to SOTA sophisticated deep learning methods that focus on enhancing detection accuracy. Methodologically, LPC-AD contributes a generic architecture LPC-Reconstruct for one to attain different trade-offs between training speed and detection accuracy. More specifically, LPC-Reconstruct is built on ideas from autoencoder for reducing redundancy in time series, latent predictive coding for capturing temporal dependence in MTS, and randomized perturbation for avoiding overfitting of anomalous dependence in the training data. We present simple instantiations of LPC-Reconstruct to attain fast training speed, where we propose a simple randomized perturbation method. The superior performance of LPC-AD over SOTA methods is validated by extensive experiments on four large real-world datasets. Experiment results also show the necessity and benefit of each component of the LPC-Reconstruct architecture and that LPC-AD is robust to hyper parameters.

Liming Wang, Hong Xie, Ye Li et al.

Template mining is one of the foundational tasks to support log analysis, which supports the diagnosis and troubleshooting of large scale Web applications. This paper develops a human-in-the-loop template mining framework to support interactive log analysis, which is highly desirable in real-world diagnosis or troubleshooting of Web applications but yet previous template mining algorithms fails to support it. We formulate three types of light-weight user feedbacks and based on them we design three atomic human-in-the-loop template mining algorithms. We derive mild conditions under which the outputs of our proposed algorithms are provably correct. We also derive upper bounds on the computational complexity and query complexity of each algorithm. We demonstrate the versatility of our proposed algorithms by combining them to improve the template mining accuracy of five representative algorithms over sixteen widely used benchmark datasets.

Zhiyong Wang, Jize Xie, Tong Yu et al.

In real-world online web systems, multiple users usually arrive sequentially into the system. For applications like click fraud and fake reviews, some users can maliciously perform corrupted (disrupted) behaviors to trick the system. Therefore, it is crucial to design efficient online learning algorithms to robustly learn from potentially corrupted user behaviors and accurately identify the corrupted users in an online manner. Existing works propose bandit algorithms robust to adversarial corruption. However, these algorithms are designed for a single user, and cannot leverage the implicit social relations among multiple users for more efficient learning. Moreover, none of them consider how to detect corrupted users online in the multiple-user scenario. In this paper, we present an important online learning problem named LOCUD to learn and utilize unknown user relations from disrupted behaviors to speed up learning, and identify the corrupted users in an online setting. To robustly learn and utilize the unknown relations among potentially corrupted users, we propose a novel bandit algorithm RCLUB-WCU. To detect the corrupted users, we devise a novel online detection algorithm OCCUD based on RCLUB-WCU's inferred user relations. We prove a regret upper bound for RCLUB-WCU, which asymptotically matches the lower bound with respect to $T$ up to logarithmic factors, and matches the state-of-the-art results in degenerate cases. We also give a theoretical guarantee for the detection accuracy of OCCUD. With extensive experiments, our methods achieve superior performance over previous bandit algorithms and high corrupted user detection accuracy.

Xuchuang Wang, Jinhang Zuo, Xutong Liu et al. · uw

This paper investigates stochastic multi-armed bandit algorithms that are robust to adversarial attacks, where an attacker can first observe the learner's action and {then} alter their reward observation. We study two cases of this model, with or without the knowledge of an attack budget $C$, defined as an upper bound of the summation of the difference between the actual and altered rewards. For both cases, we devise two types of algorithms with regret bounds having additive or multiplicative $C$ dependence terms. For the known attack budget case, we prove our algorithms achieve the regret bound of ${O}((K/Δ)\log T + KC)$ and $\tilde{O}(\sqrt{KTC})$ for the additive and multiplicative $C$ terms, respectively, where $K$ is the number of arms, $T$ is the time horizon, $Δ$ is the gap between the expected rewards of the optimal arm and the second-best arm, and $\tilde{O}$ hides the logarithmic factors. For the unknown case, we prove our algorithms achieve the regret bound of $\tilde{O}(\sqrt{KT} + KC^2)$ and $\tilde{O}(KC\sqrt{T})$ for the additive and multiplicative $C$ terms, respectively. In addition to these upper bound results, we provide several lower bounds showing the tightness of our bounds and the optimality of our algorithms. These results delineate an intrinsic separation between the bandits with attacks and corruption models [Lykouris et al., 2018].

Zhiyong Wang, Dongruo Zhou, John C. S. Lui et al.

Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work, we show that such a simple Model-based RL scheme, when equipped with optimistic and pessimistic planning procedures, achieves strong regret and sample complexity bounds in online and offline RL settings. Particularly, we demonstrate that under the conditions where the trajectory-wise reward is normalized between zero and one and the transition is time-homogenous, it achieves nearly horizon-free and second-order bounds. Nearly horizon-free means that our bounds have no polynomial dependence on the horizon of the Markov Decision Process. A second-order bound is a type of instance-dependent bound that scales with respect to the variances of the returns of the policies which can be small when the system is nearly deterministic and (or) the optimal policy has small values. We highlight that our algorithms are simple, fairly standard, and indeed have been extensively studied in the RL literature: they learn a model via MLE, build a version space around the MLE solution, and perform optimistic or pessimistic planning depending on whether operating in the online or offline mode. These algorithms do not rely on additional specialized algorithmic designs such as learning variances and performing variance-weighted learning and thus can easily leverage non-linear function approximations. The simplicity of the algorithms also implies that our horizon-free and second-order regret analysis is actually standard and mainly follows the general framework of optimism/pessimism in the face of uncertainty.

Yanqi Zhang, Yuwei Hu, Runyuan Zhao et al.

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression techniques, such as quantization and pruning, apply uniform treatment to both keys and values, and discard unimportant tokens entirely, overlooking the fine-grained distinctions in the significance of individual KV cache components. To address such limitations, we introduce \textit{DiffKV}, a novel framework for efficient KV cache compression that exploits three levels of differentiation in the KV cache: (1) the differing impact of keys and values on attention computation, (2) the varying importance of tokens, and (3) the diverse dynamic sparsity patterns across attention heads. These levels of differentiation introduce irregular memory usage patterns across different requests and attention heads, posing significant scalability challenges for memory management. To address these challenges, DiffKV proposes an on-GPU memory manager that compacts fragmented free memory list into contiguous regions in parallel, effectively translating sparsity in the KV cache into performance gains. We evaluate DiffKV on several mainstream LLMs, including the emerging thinking models that generate extended chains of thought. DiffKV is able to compress the KV cache by $2.7\times$ to $5.7\times$ with near-lossless accuracy on complex workloads requiring sophisticated reasoning and long-generation capabilities, and enhances throughput by $1.9\times$ to $5.4\times$. Source codes of DiffKV are available at https://github.com/zyqCSL/DiffKV.

Jinhang Zuo, Zhiyao Zhang, Xuchuang Wang et al.

Cooperative multi-agent multi-armed bandits (CMA2B) consider the collaborative efforts of multiple agents in a shared multi-armed bandit game. We study latent vulnerabilities exposed by this collaboration and consider adversarial attacks on a few agents with the goal of influencing the decisions of the rest. More specifically, we study adversarial attacks on CMA2B in both homogeneous settings, where agents operate with the same arm set, and heterogeneous settings, where agents have distinct arm sets. In the homogeneous setting, we propose attack strategies that, by targeting just one agent, convince all agents to select a particular target arm $T-o(T)$ times while incurring $o(T)$ attack costs in $T$ rounds. In the heterogeneous setting, we prove that a target arm attack requires linear attack costs and propose attack strategies that can force a maximum number of agents to suffer linear regrets while incurring sublinear costs and only manipulating the observations of a few target agents. Numerical experiments validate the effectiveness of our proposed attack strategies.

Jin Cheng, Xiangxiang Dai, Ningning Ding et al.

Vector data trading is essential for cross-domain learning with vector databases, yet it remains largely unexplored. We study this problem under online learning, where sellers face uncertain retrieval costs and buyers provide stochastic feedback to posted prices. Three main challenges arise: (1) heterogeneous and partial feedback in configuration learning, (2) variable and complex feedback in pricing learning, and (3) inherent coupling between configuration and pricing decisions. We propose a hierarchical bandit framework that jointly optimizes retrieval configurations and pricing. Stage I employs contextual clustering with confidence-based exploration to learn effective configurations with logarithmic regret. Stage II adopts interval-based price selection with local Taylor approximation to estimate buyer responses and achieve sublinear regret. We establish theoretical guarantees with polynomial time complexity and validate the framework on four real-world datasets, demonstrating consistent improvements in cumulative reward and regret reduction compared with existing methods.

Zeyu Zhang, Xiangxiang Dai, Ziyi Han et al.

Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static defenses degrade against evolving jailbreak behaviors, and fixed weights cannot adapt to pluralistic, time-varying safety norms. This motivates inference-time governance that steers behavior without costly retraining. To address this, we introduce the Consensus Clustering LinUCB Bandit (CCLUB), a unified framework for adaptive social alignment via system-prompt routing. CCLUB employs a conservative consensus clustering mechanism: it pools data only within the intersection of utility and safety similarity graphs, effectively preventing unsafe generalization across semantically proximal but risk-divergent contexts. Our theoretical analysis yields a sublinear regret guarantee, demonstrating near-optimal performance of CCLUB. Extensive experiments validate that CCLUB outperforms strong baselines, achieving a 10.98% improvement in cumulative reward and a 14.42% reduction in the average suboptimality gap.

Ziqun Chen, Kechao Cai, Zhuoyue Chen et al.

We study the stochastic combinatorial semi-bandit problem with unrestricted feedback delays under merit-based fairness constraints. This is motivated by applications such as crowdsourcing, and online advertising, where immediate feedback is not immediately available and fairness among different choices (or arms) is crucial. We consider two types of unrestricted feedback delays: reward-independent delays where the feedback delays are independent of the rewards, and reward-dependent delays where the feedback delays are correlated with the rewards. Furthermore, we introduce merit-based fairness constraints to ensure a fair selection of the arms. We define the reward regret and the fairness regret and present new bandit algorithms to select arms under unrestricted feedback delays based on their merits. We prove that our algorithms all achieve sublinear expected reward regret and expected fairness regret, with a dependence on the quantiles of the delay distribution. We also conduct extensive experiments using synthetic and real-world data and show that our algorithms can fairly select arms with different feedback delays.

Quanxi Zhou, Wencan Mao, Manabu Tsukada et al.

Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across tasks and scenarios. Motivated by this limitation, we propose a generalized algorithm, Feature Model-Based Enhanced Actor-Critic (FM-EAC), that integrates planning, acting, and learning for multi-task control in dynamic environments. FM-EAC combines the strengths of MBRL and MFRL and improves generalizability through the use of novel feature-based models and an enhanced actor-critic framework. Simulations in both urban and agricultural applications demonstrate that FM-EAC consistently outperforms many state-of-the-art MBRL and MFRL methods. More importantly, different sub-networks can be customized within FM-EAC according to user-specific requirements.

Xiangxiang Dai, Yuejin Xie, Maoli Liu et al.

Prompt-based offline methods are commonly used to optimize large language model (LLM) responses, but evaluating these responses is computationally intensive and often fails to accommodate diverse response styles. This study introduces a novel online evaluation framework that employs a multi-agent conversational bandit model to select optimal responses while aligning with user preferences dynamically. To tackle challenges such as high-dimensional features, large response sets, adaptive conversational needs, and multi-device access, we propose MACO, Multi-Agent Conversational Online Learning, which comprises two key components: (1) \texttt{MACO-A}: Executed by local agents, it employs an online elimination mechanism to filter out low-quality responses. (2) \texttt{MACO-S}: Executed by the cloud server, it adaptively adjusts selection strategies based on aggregated preference data. An adaptive preference mechanism triggers asynchronous conversations to enhance alignment efficiency. Theoretical analysis demonstrates that MACO achieves near-optimal regret bounds, matching state-of-the-art performance in various degenerate cases. Extensive experiments utilizing Google and OpenAI text embedding models on the real-world datasets with different response styles, combined with Llama and GPT-4o, show that MACO consistently outperforms baseline methods by at least 8.29\% across varying response set sizes and numbers of agents.

Zhuohua Li, Maoli Liu, John C. S. Lui

Conversational recommender systems have emerged as a potent solution for efficiently eliciting user preferences. These systems interactively present queries associated with "key terms" to users and leverage user feedback to estimate user preferences more efficiently. Nonetheless, most existing algorithms adopt a centralized approach. In this paper, we introduce FedConPE, a phase elimination-based federated conversational bandit algorithm, where $M$ agents collaboratively solve a global contextual linear bandit problem with the help of a central server while ensuring secure data management. To effectively coordinate all the clients and aggregate their collected data, FedConPE uses an adaptive approach to construct key terms that minimize uncertainty across all dimensions in the feature space. Furthermore, compared with existing federated linear bandit algorithms, FedConPE offers improved computational and communication efficiency as well as enhanced privacy protections. Our theoretical analysis shows that FedConPE is minimax near-optimal in terms of cumulative regret. We also establish upper bounds for communication costs and conversation frequency. Comprehensive evaluations demonstrate that FedConPE outperforms existing conversational bandit algorithms while using fewer conversations.

Hantao Yang, Xutong Liu, Zhiyong Wang et al. · uw

We study the problem of federated contextual combinatorial cascading bandits, where $|\mathcal{U}|$ agents collaborate under the coordination of a central server to provide tailored recommendations to the $|\mathcal{U}|$ corresponding users. Existing works consider either a synchronous framework, necessitating full agent participation and global synchronization, or assume user homogeneity with identical behaviors. We overcome these limitations by considering (1) federated agents operating in an asynchronous communication paradigm, where no mandatory synchronization is required and all agents communicate independently with the server, (2) heterogeneous user behaviors, where users can be stratified into $J \le |\mathcal{U}|$ latent user clusters, each exhibiting distinct preferences. For this setting, we propose a UCB-type algorithm with delicate communication protocols. Through theoretical analysis, we give sub-linear regret bounds on par with those achieved in the synchronous framework, while incurring only logarithmic communication costs. Empirical evaluation on synthetic and real-world datasets validates our algorithm's superior performance in terms of regrets and communication costs.

Manhin Poon, XiangXiang Dai, Xutong Liu et al. · uw

Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query. We study the problem of adaptive multi-LLM selection in an online setting, where the learner interacts with users through multi-step query refinement and must choose LLMs sequentially without access to offline datasets or model internals. A key challenge arises from unstructured context evolution: the prompt dynamically changes in response to previous model outputs via a black-box process, which cannot be simulated, modeled, or learned. To address this, we propose the first contextual bandit framework for sequential LLM selection under unstructured prompt dynamics. We formalize a notion of myopic regret and develop a LinUCB-based algorithm that provably achieves sublinear regret without relying on future context prediction. We further introduce budget-aware and positionally-aware (favoring early-stage satisfaction) extensions to accommodate variable query costs and user preferences for early high-quality responses. Our algorithms are theoretically grounded and require no offline fine-tuning or dataset-specific training. Experiments on diverse benchmarks demonstrate that our methods outperform existing LLM routing strategies in both accuracy and cost-efficiency, validating the power of contextual bandits for real-time, adaptive LLM selection.

Xuchuang Wang, Maoli Liu, Xutong Liu et al.

Quantum networks (QNs) transmit delicate quantum information across noisy quantum channels. Crucial applications, like quantum key distribution (QKD) and distributed quantum computation (DQC), rely on efficient quantum information transmission. Learning the best path between a pair of end nodes in a QN is key to enhancing such applications. This paper addresses learning the best path in a QN in the online learning setting. We explore two types of feedback: "link-level" and "path-level". Link-level feedback pertains to QNs with advanced quantum switches that enable link-level benchmarking. Path-level feedback, on the other hand, is associated with basic quantum switches that permit only path-level benchmarking. We introduce two online learning algorithms, BeQuP-Link and BeQuP-Path, to identify the best path using link-level and path-level feedback, respectively. To learn the best path, BeQuP-Link benchmarks the critical links dynamically, while BeQuP-Path relies on a subroutine, transferring path-level observations to estimate link-level parameters in a batch manner. We analyze the quantum resource complexity of these algorithms and demonstrate that both can efficiently and, with high probability, determine the best path. Finally, we perform NetSquid-based simulations and validate that both algorithms accurately and efficiently identify the best path.

Ruhan Wang, Zhiyong Wang, Chengkai Huang et al.

For question-answering (QA) tasks, in-context learning (ICL) enables language models to generate responses without modifying their parameters by leveraging examples provided in the input. However, the effectiveness of ICL heavily depends on the availability of high-quality examples, which are often scarce due to data privacy constraints, annotation costs, and distribution disparities. A natural solution is to utilize examples stored on client devices, but existing approaches either require transmitting model parameters - incurring significant communication overhead - or fail to fully exploit local datasets, limiting their effectiveness. To address these challenges, we propose Federated In-Context Learning (Fed-ICL), a general framework that enhances ICL through an iterative, collaborative process. Fed-ICL progressively refines responses by leveraging multi-round interactions between clients and a central server, improving answer quality without the need to transmit model parameters. We establish theoretical guarantees for the convergence of Fed-ICL and conduct extensive experiments on standard QA benchmarks, demonstrating that our proposed approach achieves strong performance while maintaining low communication costs.

Zhuohua Li, Maoli Liu, Xiangxiang Dai et al.

The contextual multi-armed bandit (MAB) problem is crucial in sequential decision-making. A line of research, known as online clustering of bandits, extends contextual MAB by grouping similar users into clusters, utilizing shared features to improve learning efficiency. However, existing algorithms, which rely on the upper confidence bound (UCB) strategy, struggle to gather adequate statistical information to accurately identify unknown user clusters. As a result, their theoretical analyses require several strong assumptions about the "diversity" of contexts generated by the environment, leading to impractical settings, complicated analyses, and poor practical performance. Removing these assumptions has been a long-standing open problem in the clustering of bandits literature. In this paper, we provide two solutions to this open problem. First, following the i.i.d. context generation setting in existing studies, we propose two novel algorithms, UniCLUB and PhaseUniCLUB, which incorporate enhanced exploration mechanisms to accelerate cluster identification. Remarkably, our algorithms require substantially weaker assumptions while achieving regret bounds comparable to prior work. Second, inspired by the smoothed analysis framework, we propose a more practical setting that eliminates the requirement for i.i.d. context generation used in previous studies, thus enhancing the performance of existing algorithms for online clustering of bandits. Our technique can be applied to both graph-based and set-based clustering of bandits frameworks. Extensive evaluations on both synthetic and real-world datasets demonstrate that our proposed algorithms consistently outperform existing approaches.

Xutong Liu, Xiangxiang Dai, Xuchuang Wang et al. · uw

We introduce a novel framework called combinatorial logistic bandits (CLogB), where in each round, a subset of base arms (called the super arm) is selected, with the outcome of each base arm being binary and its expectation following a logistic parametric model. The feedback is governed by a general arm triggering process. Our study covers CLogB with reward functions satisfying two smoothness conditions, capturing application scenarios such as online content delivery, online learning to rank, and dynamic channel allocation. We first propose a simple yet efficient algorithm, CLogUCB, utilizing a variance-agnostic exploration bonus. Under the 1-norm triggering probability modulated (TPM) smoothness condition, CLogUCB achieves a regret bound of $\tilde{O}(d\sqrt{κKT})$, where $\tilde{O}$ ignores logarithmic factors, $d$ is the dimension of the feature vector, $κ$ represents the nonlinearity of the logistic model, and $K$ is the maximum number of base arms a super arm can trigger. This result improves on prior work by a factor of $\tilde{O}(\sqrtκ)$. We then enhance CLogUCB with a variance-adaptive version, VA-CLogUCB, which attains a regret bound of $\tilde{O}(d\sqrt{KT})$ under the same 1-norm TPM condition, improving another $\tilde{O}(\sqrtκ)$ factor. VA-CLogUCB shows even greater promise under the stronger triggering probability and variance modulated (TPVM) condition, achieving a leading $\tilde{O}(d\sqrt{T})$ regret, thus removing the additional dependency on the action-size $K$. Furthermore, we enhance the computational efficiency of VA-CLogUCB by eliminating the nonconvex optimization process when the context feature map is time-invariant while maintaining the tight $\tilde{O}(d\sqrt{T})$ regret. Finally, experiments on synthetic and real-world datasets demonstrate the superior performance of our algorithms compared to benchmark algorithms.

Xiaoxin Su, Yipeng Zhou, Laizhong Cui et al.

In Federated Learning (FL) paradigm, a parameter server (PS) concurrently communicates with distributed participating clients for model collection, update aggregation, and model distribution over multiple rounds, without touching private data owned by individual clients. FL is appealing in preserving data privacy; yet the communication between the PS and scattered clients can be a severe bottleneck. Model compression algorithms, such as quantization and sparsification, have been suggested but they generally assume a fixed code length, which does not reflect the heterogeneity and variability of model updates. In this paper, through both analysis and experiments, we show strong evidences that variable-length is beneficial for compression in FL. We accordingly present Fed-CVLC (Federated Learning Compression with Variable-Length Codes), which fine-tunes the code length in response of the dynamics of model updates. We develop optimal tuning strategy that minimizes the loss function (equivalent to maximizing the model utility) subject to the budget for communication. We further demonstrate that Fed-CVLC is indeed a general compression design that bridges quantization and sparsification, with greater flexibility. Extensive experiments have been conducted with public datasets to demonstrate that Fed-CVLC remarkably outperforms state-of-the-art baselines, improving model utility by 1.50%-5.44%, or shrinking communication traffic by 16.67%-41.61%.

Ziyi Han, Huanyu Wang, Zeyu Zhang et al. · uw

Low-Rank Adaptation (LoRA) has emerged as a widely used technique for adapting large language models (LLMs) to new domains, due to its modular design and broad availability on platforms such as HuggingFace. This availability has motivated efforts to reuse existing LoRAs for domain generalization. However, existing methods often rely on explicit task labels or additional training, which are impractical for deployment. Moreover, they typically activate a fixed number of entire LoRA modules, leading to parameter redundancy or insufficiency that degrade performance. In this paper, we propose \texttt{HiLoRA}, a training-free framework that performs adaptive hierarchical routing over LoRA pools. Drawing on structural properties of LoRA, we define rank-one components (ROCs), in which each rank parameter is regarded as an independent unit. For a given input sequence, \texttt{HiLoRA} first adaptively selects a subset of LoRAs and determines their ROC allocation based on Gaussian likelihoods at the sequence level. At the token level, it further refines routing by activating only the most informative ROCs. We further provide theoretical guarantees that \texttt{HiLoRA} selects the most relevant LoRAs with high probability. Extensive experiments show that \texttt{HiLoRA} achieves substantial improvements in domain generalization, with accuracy gains of up to {\small $55\%$} over state-of-the-art baselines, while maintaining comparable inference throughput.

Maoli Liu, Zhuohua Li, Xiangxiang Dai et al.

Conversational recommender systems proactively query users with relevant "key terms" and leverage the feedback to elicit users' preferences for personalized recommendations. Conversational contextual bandits, a prevalent approach in this domain, aim to optimize preference learning by balancing exploitation and exploration. However, several limitations hinder their effectiveness in real-world scenarios. First, existing algorithms employ key term selection strategies with insufficient exploration, often failing to thoroughly probe users' preferences and resulting in suboptimal preference estimation. Second, current algorithms typically rely on deterministic rules to initiate conversations, causing unnecessary interactions when preferences are well-understood and missed opportunities when preferences are uncertain. To address these limitations, we propose three novel algorithms: CLiSK, CLiME, and CLiSK-ME. CLiSK introduces smoothed key term contexts to enhance exploration in preference learning, CLiME adaptively initiates conversations based on preference uncertainty, and CLiSK-ME integrates both techniques. We theoretically prove that all three algorithms achieve a tighter regret upper bound of $O(\sqrt{dT\log{T}})$ with respect to the time horizon $T$, improving upon existing methods. Additionally, we provide a matching lower bound $Ω(\sqrt{dT})$ for conversational bandits, demonstrating that our algorithms are nearly minimax optimal. Extensive evaluations on both synthetic and real-world datasets show that our approaches achieve at least a 14.6% improvement in cumulative regret.

Jiahang Sun, Zhiyong Wang, Runhan Yang et al.

Large language models (LLMs) have been adopted to solve sequential decision-making tasks such as multi-armed bandits (MAB), in which an LLM is directly instructed to select the arms to pull in every iteration. However, this paradigm of direct arm selection using LLMs has been shown to be suboptimal in many MAB tasks. Therefore, we propose an alternative approach which combines the strengths of classical MAB and LLMs. Specifically, we adopt a classical MAB algorithm as the high-level framework and leverage the strong in-context learning capability of LLMs to perform the sub-task of reward prediction. Firstly, we incorporate the LLM-based reward predictor into the classical Thompson sampling (TS) algorithm and adopt a decaying schedule for the LLM temperature to ensure a transition from exploration to exploitation. Next, we incorporate the LLM-based reward predictor (with a temperature of 0) into a regression oracle-based MAB algorithm equipped with an explicit exploration mechanism. We also extend our TS-based algorithm to dueling bandits where only the preference feedback between pairs of arms is available, which requires non-trivial algorithmic modifications. We conduct empirical evaluations using both synthetic MAB tasks and experiments designed using real-world text datasets, in which the results show that our algorithms consistently outperform previous baseline methods based on direct arm selection. Interestingly, we also demonstrate that in challenging tasks where the arms lack semantic meanings that can be exploited by the LLM, our approach achieves considerably better performance than LLM-based direct arm selection.

Zhiyong Wang, Jize Xie, Yi Chen et al.

We investigate the non-stationary stochastic linear bandit problem where the reward distribution evolves each round. Existing algorithms characterize the non-stationarity by the total variation budget $B_K$, which is the summation of the change of the consecutive feature vectors of the linear bandits over $K$ rounds. However, such a quantity only measures the non-stationarity with respect to the expectation of the reward distribution, which makes existing algorithms sub-optimal under the general non-stationary distribution setting. In this work, we propose algorithms that utilize the variance of the reward distribution as well as the $B_K$, and show that they can achieve tighter regret upper bounds. Specifically, we introduce two novel algorithms: Restarted Weighted$\text{OFUL}^+$ and Restarted $\text{SAVE}^+$. These algorithms address cases where the variance information of the rewards is known and unknown, respectively. Notably, when the total variance $V_K$ is much smaller than $K$, our algorithms outperform previous state-of-the-art results on non-stationary stochastic linear bandits under different settings. Experimental evaluations further validate the superior performance of our proposed algorithms over existing works.

Xutong Liu, Xiangxiang Dai, Jinhang Zuo et al. · uw

The combinatorial multi-armed bandit (CMAB) is a fundamental sequential decision-making framework, extensively studied over the past decade. However, existing work primarily focuses on the online setting, overlooking the substantial costs of online interactions and the readily available offline datasets. To overcome these limitations, we introduce Off-CMAB, the first offline learning framework for CMAB. Central to our framework is the combinatorial lower confidence bound (CLCB) algorithm, which combines pessimistic reward estimations with combinatorial solvers. To characterize the quality of offline datasets, we propose two novel data coverage conditions and prove that, under these conditions, CLCB achieves a near-optimal suboptimality gap, matching the theoretical lower bound up to a logarithmic factor. We validate Off-CMAB through practical applications, including learning to rank, large language model (LLM) caching, and social influence maximization, showing its ability to handle nonlinear reward functions, general feedback models, and out-of-distribution action samples that excludes optimal or even feasible actions. Extensive experiments on synthetic and real-world datasets further highlight the superior performance of CLCB.

Ziyi Han, Xutong Liu, Ruiting Zhou et al. · uw

Sparse Mixture of Experts (SMoE) has become a preferred architecture for scaling Transformer capacity without increasing computational cost, as it activates only a small subset of experts for each input. However, deploying such an approach for \textit{online inference} remains challenging due to the large size of a full SMoE model and the complexity of expert routing, especially in resource-constrained edge networks. Moreover, during the online inference, task information is often unavailable, making the task-level routing error-prone. In this work, we propose a novel tree-structured adaptive neural bandit router, \texttt{Tanbr}, to enable efficient and reliable online MoE inference. Instead of relying on explicit task tags, \texttt{Tanbr} estimates the task distribution over time from historical data and uses it to guide task-aware expert merging within a given pre-trained MoE. To handle the large continuous space of merging weights, \texttt{Tanbr} employs a binary tree to progressively partition the space and generate finer candidate weights. It then applies a neural bandit to learn the non-linear mapping from merging weight to model performance and decides optimal expert merging. We prove that \texttt{Tanbr} achieves a sublinear regret bound of {\small $\mathcal{O}(\sqrt{T} \log(T))$} over {\small $T$} rounds, despite operating over a continuous decision space, matching regret bounds compared to existing methods. Extensive experiments show that \texttt{Tanbr} reduces inference latency by at least {\small $45\%$} and memory usage by up to {\small $25\%$}, while maintaining a high accuracy compared to many state-of-the-art methods.

Xutong Liu, Baran Atalar, Xiangxiang Dai et al. · uw

Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges. Caching inference responses, allowing them to be retrieved without another forward pass through the LLM, has emerged as one possible solution. Traditional exact-match caching, however, overlooks the semantic similarity between queries, leading to unnecessary recomputation. Semantic caching addresses this by retrieving responses based on semantic similarity, but introduces a fundamentally different cache eviction problem: one must account for mismatch costs between incoming queries and cached responses. Moreover, key system parameters, such as query arrival probabilities and serving costs, are often unknown and must be learned over time. Existing semantic caching methods are largely ad-hoc, lacking theoretical foundations and unable to adapt to real-world uncertainty. In this paper, we present a principled, learning-based framework for semantic cache eviction under unknown query and cost distributions. We formulate both offline optimization and online learning variants of the problem, and develop provably efficient algorithms with state-of-the-art guarantees. We also evaluate our framework on a synthetic dataset, showing that our proposed algorithms perform matching or superior performance compared with baselines.

Xuchuang Wang, Bo Sun, Hedyeh Beyhaghi et al.

This paper introduces a novel multi-agent ski-rental problem that generalizes the classical ski-rental dilemma to a group setting where agents incur individual and shared costs. In our model, each agent can either rent at a fixed daily cost, or purchase a pass at an individual cost, with an additional third option of a discounted group pass available to all. We consider scenarios in which agents' active days differ, leading to dynamic states as agents drop out of the decision process. To address this problem from different perspectives, we define three distinct competitive ratios: overall, state-dependent, and individual rational. For each objective, we design and analyze optimal deterministic and randomized policies. Our deterministic policies employ state-aware threshold functions that adapt to the dynamic states, while our randomized policies sample and resample thresholds from tailored state-aware distributions. The analysis reveals that symmetric policies, in which all agents use the same threshold, outperform asymmetric ones. Our results provide competitive ratio upper and lower bounds and extend classical ski-rental insights to multi-agent settings, highlighting both theoretical and practical implications for group decision-making under uncertainty.

Jianhao He, John C. S. Lui

This paper considers the projection-free sparse convex optimization problem for the vector domain and the matrix domain, which covers a large number of important applications in machine learning and data science. For the vector domain $\mathcal{D} \subset \mathbb{R}^d$, we propose two quantum algorithms for sparse constraints that finds a $\varepsilon$-optimal solution with the query complexity of $O(\sqrt{d}/\varepsilon)$ and $O(1/\varepsilon)$ by using the function value oracle, reducing a factor of $O(\sqrt{d})$ and $O(d)$ over the best classical algorithm, respectively, where $d$ is the dimension. For the matrix domain $\mathcal{D} \subset \mathbb{R}^{d\times d}$, we propose two quantum algorithms for nuclear norm constraints that improve the time complexity to $\tilde{O}(rd/\varepsilon^2)$ and $\tilde{O}(\sqrt{r}d/\varepsilon^3)$ for computing the update step, reducing at least a factor of $O(\sqrt{d})$ over the best classical algorithm, where $r$ is the rank of the gradient matrix. Our algorithms show quantum advantages in projection-free sparse convex optimization problems as they outperform the optimal classical methods in dependence on the dimension $d$.

Xiangxiang Dai, Xiaowei Sun, Jinhang Zuo et al. · uw

Co-branding has become a vital strategy for businesses aiming to expand market reach within recommendation systems. However, identifying effective cross-industry partnerships remains challenging due to resource imbalances, uncertain brand willingness, and ever-changing market conditions. In this paper, we provide the first systematic study of this problem and propose a unified online-offline framework to enable co-branding recommendations. Our approach begins by constructing a bipartite graph linking ``initiating'' and ``target'' brands to quantify co-branding probabilities and assess market benefits. During the online learning phase, we dynamically update the graph in response to market feedback, while striking a balance between exploring new collaborations for long-term gains and exploiting established partnerships for immediate benefits. To address the high initial co-branding costs, our framework mitigates redundant exploration, thereby enhancing short-term performance while ensuring sustainable strategic growth. In the offline optimization phase, our framework consolidates the interests of multiple sub-brands under the same parent brand to maximize overall returns, avoid excessive investment in single sub-brands, and reduce unnecessary costs associated with over-prioritizing a single sub-brand. We present a theoretical analysis of our approach, establishing a highly nontrivial sublinear regret bound for online learning in the complex co-branding problem, and enhancing the approximation guarantee for the NP-hard offline budget allocation optimization. Experiments on both synthetic and real-world co-branding datasets demonstrate the practical effectiveness of our framework, with at least 12\% improvement.

Jingyuan Liu, Zeyu Zhang, Xuchuang Wang et al.

Contextual multi-armed bandit is a fundamental learning framework for making a sequence of decisions, e.g., advertising recommendations for a sequence of arriving users. Recent works have shown that clustering these users based on the similarity of their learned preferences can accelerate the learning. However, prior work has primarily focused on the online setting, which requires continually collecting user data, ignoring the offline data widely available in many applications. To tackle these limitations, we study the offline clustering of bandits (Off-ClusBand) problem, which studies how to use the offline dataset to learn cluster properties and improve decision-making. The key challenge in Off-ClusBand arises from data insufficiency for users: unlike the online case where we continually learn from online data, in the offline case, we have a fixed, limited dataset to work from and thus must determine whether we have enough data to confidently cluster users together. To address this challenge, we propose two algorithms: Off-C2LUB, which we show analytically and experimentally outperforms existing methods under limited offline user data, and Off-CLUB, which may incur bias when data is sparse but performs well and nearly matches the lower bound when data is sufficient. We experimentally validate these results on both real and synthetic datasets.

Xuchuang Wang, Qirun Zeng, Jinhang Zuo et al.

This paper investigates the fusion of absolute (reward) and relative (dueling) feedback in stochastic bandits, where both feedback types are gathered in each decision round. We derive a regret lower bound, demonstrating that an efficient algorithm may incur only the smaller among the reward and dueling-based regret for each individual arm. We propose two fusion approaches: (1) a simple elimination fusion algorithm that leverages both feedback types to explore all arms and unifies collected information by sharing a common candidate arm set, and (2) a decomposition fusion algorithm that selects the more effective feedback to explore the corresponding arms and randomly assigns one feedback type for exploration and the other for exploitation in each round. The elimination fusion experiences a suboptimal multiplicative term of the number of arms in regret due to the intrinsic suboptimality of dueling elimination. In contrast, the decomposition fusion achieves regret matching the lower bound up to a constant under a common assumption. Extensive experiments confirm the efficacy of our algorithms and theoretical results.

Zhiyong Wang, Chen Yang, John C. S. Lui et al.

In this work, we study offline reinforcement learning (RL) with zero-shot generalization property (ZSG), where the agent has access to an offline dataset including experiences from different environments, and the goal of the agent is to train a policy over the training environments which performs well on test environments without further interaction. Existing work showed that classical offline RL fails to generalize to new, unseen environments. We propose pessimistic empirical risk minimization (PERM) and pessimistic proximal policy optimization (PPPO), which leverage pessimistic policy evaluation to guide policy learning and enhance generalization. We show that both PERM and PPPO are capable of finding a near-optimal policy with ZSG. Our result serves as a first step in understanding the foundation of the generalization phenomenon in offline reinforcement learning.

Zhiyong Wang, Jiahang Sun, Mingze Kong et al.

The contextual multi-armed bandit (MAB) is a widely used framework for problems requiring sequential decision-making under uncertainty, such as recommendation systems. In applications involving a large number of users, the performance of contextual MAB can be significantly improved by facilitating collaboration among multiple users. This has been achieved by the clustering of bandits (CB) methods, which adaptively group the users into different clusters and achieve collaboration by allowing the users in the same cluster to share data. However, classical CB algorithms typically rely on numerical reward feedback, which may not be practical in certain real-world applications. For instance, in recommendation systems, it is more realistic and reliable to solicit preference feedback between pairs of recommended items rather than absolute rewards. To address this limitation, we introduce the first "clustering of dueling bandit algorithms" to enable collaborative decision-making based on preference feedback. We propose two novel algorithms: (1) Clustering of Linear Dueling Bandits (COLDB) which models the user reward functions as linear functions of the context vectors, and (2) Clustering of Neural Dueling Bandits (CONDB) which uses a neural network to model complex, non-linear user reward functions. Both algorithms are supported by rigorous theoretical analyses, demonstrating that user collaboration leads to improved regret bounds. Extensive empirical evaluations on synthetic and real-world datasets further validate the effectiveness of our methods, establishing their potential in real-world applications involving multiple users with preference-based feedback.

Xutong Liu, Siwei Wang, Jinhang Zuo et al.

We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a general arm triggering process. Compared with existing CMAB works, CMAB-MT not only enhances the modeling power but also allows improved results by leveraging distinct statistical properties for multivariant random variables. For CMAB-MT, we propose a general 1-norm multivariant and triggering probability-modulated smoothness condition, and an optimistic CUCB-MT algorithm built upon this condition. Our framework can include many important problems as applications, such as episodic reinforcement learning (RL) and probabilistic maximum coverage for goods distribution, all of which meet the above smoothness condition and achieve matching or improved regret bounds compared to existing works. Through our new framework, we build the first connection between the episodic RL and CMAB literature, by offering a new angle to solve the episodic RL through the lens of CMAB, which may encourage more interactions between these two important directions.

Behnaz Soltani, Yipeng Zhou, Venus Haghighi et al.

In traditional machine learning, it is trivial to conduct model evaluation since all data samples are managed centrally by a server. However, model evaluation becomes a challenging problem in federated learning (FL), which is called federated evaluation in this work. This is because clients do not expose their original data to preserve data privacy. Federated evaluation plays a vital role in client selection, incentive mechanism design, malicious attack detection, etc. In this paper, we provide the first comprehensive survey of existing federated evaluation methods. Moreover, we explore various applications of federated evaluation for enhancing FL performance and finally present future research directions by envisioning some challenges.