Mengfan Xu

Mengfan Xu, Diego Klabjan

We study Pareto optimality in multi-objective multi-armed bandit by providing a formulation of adversarial multi-objective multi-armed bandit and defining its Pareto regrets that can be applied to both stochastic and adversarial settings. The regrets do not rely on any scalarization functions and reflect Pareto optimality compared to scalarized regrets. We also present new algorithms assuming both with and without prior information of the multi-objective multi-armed bandit setting. The algorithms are shown optimal in adversarial settings and nearly optimal up to a logarithmic factor in stochastic settings simultaneously by our established upper bounds and lower bounds on Pareto regrets. Moreover, the lower bound analyses show that the new regrets are consistent with the existing Pareto regret for stochastic settings and extend an adversarial attack mechanism from bandit to the multi-objective one.

Mengfan Xu, Diego Klabjan

We study a decentralized multi-agent multi-armed bandit problem in which multiple clients are connected by time dependent random graphs provided by an environment. The reward distributions of each arm vary across clients and rewards are generated independently over time by an environment based on distributions that include both sub-exponential and sub-gaussian distributions. Each client pulls an arm and communicates with neighbors based on the graph provided by the environment. The goal is to minimize the overall regret of the entire system through collaborations. To this end, we introduce a novel algorithmic framework, which first provides robust simulation methods for generating random graphs using rapidly mixing Markov chains or the random graph model, and then combines an averaging-based consensus approach with a newly proposed weighting technique and the upper confidence bound to deliver a UCB-type solution. Our algorithms account for the randomness in the graphs, removing the conventional doubly stochasticity assumption, and only require the knowledge of the number of clients at initialization. We derive optimal instance-dependent regret upper bounds of order $\log{T}$ in both sub-gaussian and sub-exponential environments, and a nearly optimal mean-gap independent regret upper bound of order $\sqrt{T}\log T$ up to a $\log T$ factor. Importantly, our regret bounds hold with high probability and capture graph randomness, whereas prior works consider expected regret under assumptions and require more stringent reward distributions.

Mengfan Xu, Diego Klabjan

Multi-armed Bandit motivates methods with provable upper bounds on regret and also the counterpart lower bounds have been extensively studied in this context. Recently, Multi-agent Multi-armed Bandit has gained significant traction in various domains, where individual clients face bandit problems in a distributed manner and the objective is the overall system performance, typically measured by regret. While efficient algorithms with regret upper bounds have emerged, limited attention has been given to the corresponding regret lower bounds, except for a recent lower bound for adversarial settings, which, however, has a gap with let known upper bounds. To this end, we herein provide the first comprehensive study on regret lower bounds across different settings and establish their tightness. Specifically, when the graphs exhibit good connectivity properties and the rewards are stochastically distributed, we demonstrate a lower bound of order $O(\log T)$ for instance-dependent bounds and $\sqrt{T}$ for mean-gap independent bounds which are tight. Assuming adversarial rewards, we establish a lower bound $O(T^{\frac{2}{3}})$ for connected graphs, thereby bridging the gap between the lower and upper bound in the prior work. We also show a linear regret lower bound when the graph is disconnected. While previous works have explored these settings with upper bounds, we provide a thorough study on tight lower bounds.

Shu Wan, Chen Zheng, Zhonggen Sun et al.

Uplift modeling is a rapidly growing approach that utilizes causal inference and machine learning methods to directly estimate the heterogeneous treatment effects, which has been widely applied to various online marketplaces to assist large-scale decision-making in recent years. The existing popular models, like causal forest (CF), are limited to either discrete treatments or posing parametric assumptions on the outcome-treatment relationship that may suffer model misspecification. However, continuous treatments (e.g., price, duration) often arise in marketplaces. To alleviate these restrictions, we use a kernel-based doubly robust estimator to recover the non-parametric dose-response functions that can flexibly model continuous treatment effects. Moreover, we propose a generic distance-based splitting criterion to capture the heterogeneity for the continuous treatments. We call the proposed algorithm generalized causal forest (GCF) as it generalizes the use case of CF to a much broader setting. We show the effectiveness of GCF by deriving the asymptotic property of the estimator and comparing it to popular uplift modeling methods on both synthetic and real-world datasets. We implement GCF on Spark and successfully deploy it into a large-scale online pricing system at a leading ride-sharing company. Online A/B testing results further validate the superiority of GCF.

Amirmahdi Mirfakhar, Xuchuang Wang, Mengfan Xu et al.

Two-sided matching markets rely on preferences from both sides, yet it is often impractical to evaluate preferences. Participants, therefore, conduct a limited number of interviews, which provide early, noisy impressions and shape final decisions. We study bandit learning in matching markets with interviews, modeling interviews as \textit{low-cost hints} that reveal partial preference information to both sides. Our framework departs from existing work by allowing firm-side uncertainty: firms, like agents, may be unsure of their own preferences and can make early hiring mistakes by hiring less preferred agents. To handle this, we extend the firm's action space to allow \emph{strategic deferral} (choosing not to hire in a round), enabling recovery from suboptimal hires and supporting decentralized learning without coordination. We design novel algorithms for (i) a centralized setting with an omniscient interview allocator and (ii) decentralized settings with two types of firm-side feedback. Across all settings, our algorithms achieve time-independent regret, a substantial improvement over the $O(\log T)$ regret bounds known for learning stable matchings without interviews. Also, under mild structured markets, decentralized performance matches the centralized counterpart up to polynomial factors in the number of agents and firms.

Chengyu Du, Mengfan Xu

Stochastic bandit algorithms are usually analyzed under a mean-reward criterion, yet many problems favor arms with strong upper-tail performance, which we study herein. For a fixed miscoverage level \(α\), the natural upper-tail target of arm \(j\) is the upper endpoint \(F_j^{-1}(1-α/2)\) of a central prediction interval. This target can rank arms differently from their means, creating a central mismatch with the classical bandit objective. To this end, we propose ACP-UCB1, a conformal-style policy that combines an adaptive conformal estimate of the upper endpoint with a UCB-type optimism bonus. The technical challenge is that the conformity scores used by ACP-UCB1 are recomputed from evolving empirical quantile estimates and evaluated at an adaptive level. We control this endpoint through reward-quantile concentration, a perturbation argument for recomputed score quantiles, and deterministic localization of the adaptive level. ACP-UCB1 achieves logarithmic upper-quantile regret with per-arm contribution \(O(\nicefrac{\log n}{Δ_j^{\mathrm{ACP}}})\). We also provide metric-specific regret decompositions comparing ACP-UCB1 with UCB1 and use numerical experiments to validate performance and improvement.

Mengfan Xu

Recent developments in digital platforms have highlighted the prevalence of open systems, where agents can arrive and depart over time. While bandit learning in open systems has recently received initial attention, existing work imposes structural assumptions that are frequently violated in practice. A learning paradigm for general open systems creates fresh challenges: newly arriving agents induce endogenous non-stationarity; agent patterns determine how quickly information accumulates; and new agents make regret scale further with the time horizon. To this end, we formulate a unified open-system bandit problem with general dynamics, including heterogeneous rewards and general agent patterns. We introduce new concepts to capture the inherent complexities: the \emph{pre-training degree} of new agents quantifies how much information an agent carries upon entry, \emph{stability} measures the impact of new agents on the system, and \emph{global dynamic regret} compares the cumulative expected reward of all active agents with that of the varying optimal arms. We develop certified global-UCB learning methodologies with provable guarantees. Our regret bounds reveal that entry uncertainty enters linearly via the pre-training degree, while in stable regimes, regret is governed by the time needed to identify a persistent optimal arm, as well as by the agent patterns. We further show that these dependencies are tight via lower bounds in hard instances.

John Wang, Mengfan Xu

We study multi-objective multi-agent multi-armed bandits (MO-MA-MAB) under stochastic rewards, where agents observe heterogeneous reward vectors and communicate over time-varying graphs. We formulate this emerging problem setting to address \emph{efficient learning}, measured by Pareto regret, and incorporate \emph{fair learning} as an additional goal, captured via social welfare. To measure efficiency, we formulate Pareto regret and develop \textsc{Pareto UCB1 Gossip}, whose novel exploration radius explicitly separates statistical uncertainty in Pareto-based inference from consensus error. To express the fairness constraint, we formulate a Nash Social Welfare objective over preference-scalarized rewards and propose \textsc{Simulated NSW UCB Gossip}, which integrates preference-based reward simulation, gossip-based utility estimation, and UCB-style exploration. We prove that \textsc{Pareto UCB1 Gossip} achieves \(\mathcal{O}(\log T)\) regret and an instance-independent rate of \(\mathcal{O}(\sqrt{T})\), while \textsc{Simulated NSW UCB Gossip} achieves an instance-independent regret bound of \(\mathcal{O}(T^{3/4})\). This separation reveals the cost of imposing the fairness constraint to our efficiency objective: fairness limits information aggregation and slows convergence. Experiments show that our methods consistently outperform baselines, improving performance by approximately \(100\%\) and \(50\%\) in the efficiency and fairness settings, respectively.

Changkun Guan, Mengfan Xu

Multi-objective bandits have attracted increasing attention because of their broad applicability and mathematical elegance, where the reward of each arm is a multi-dimensional vector rather than a scalar. This naturally introduces Pareto order relations and Pareto regret. A long-standing question in this area is whether performance is fundamentally harder to optimize because of this added complexity. A recent surprising result shows that, in the adversarial setting, Pareto regret is no larger than classical regret; however, in the stochastic setting, where the regret notion is different, the picture remains unclear. In fact, existing work suggests that Pareto regret in the stochastic case increases with the dimensionality. This controversial yet subtle phenomenon motivates our central question: \emph{are multi-objective bandits actually harder than single-objective ones?} We answer this question in full by showing that, in the stochastic setting, Pareto regret is in fact governed by the maximum sub-optimality gap \(g^\dagger\), and hence by the minimum marginal regret of order \(Ω(\frac{K\log T}{g^\dagger})\). We further develop a new algorithm that achieves Pareto regret of order \(O(\frac{K\log T}{g^\dagger})\), and is therefore optimal. The algorithm leverages a nested two-layer uncertainty quantification over both arms and objectives through upper and lower confidence bound estimators. It combines a top-two racing strategy for arm selection with an uncertainty-greedy rule for dimension selection. Together, these components balance exploration and exploitation across the two layers. We also conduct comprehensive numerical experiments to validate the proposed algorithm, showing the desired regret guarantee and significant gains over benchmark methods.

Wei Shen, Zhang Yaxiang, Minhui Huang et al.

With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a novel memory-efficient training paradigm called Momentum Low-rank compression (MLorc). The key idea of MLorc is to compress and reconstruct the momentum of matrix parameters during training to reduce memory consumption. Compared to LoRA, MLorc avoids enforcing a fixed-rank constraint on weight update matrices and thus enables full-parameter learning. Compared to GaLore, MLorc directly compress the momentum rather than gradients, thereby better preserving the training dynamics of full-parameter fine-tuning. We provide a theoretical guarantee for its convergence under mild assumptions. Empirically, MLorc consistently outperforms other memory-efficient training methods, matches or even exceeds the performance of full fine-tuning at small ranks (e.g., $r=4$), and generalizes well across different optimizers -- all while not compromising time or memory efficiency.

Jingyuan Liu, Hao Qiu, Lin Yang et al.

We study the distributed multi-agent multi-armed bandit problem with heterogeneous rewards over random communication graphs. Uniquely, at each time step $t$ agents communicate over a time-varying random graph $G_t$ generated by applying the Erdős-Rényi model to a fixed connected base graph $G$ (for classical Erdős-Rényi graphs, $G$ is a complete graph), where each potential edge in $G$ is randomly and independently present with the link probability $p$. Notably, the resulting random graph is not necessarily connected at each time step. Each agent's arm rewards follow time-invariant distributions, and the reward distribution for the same arm may differ across agents. The goal is to minimize the cumulative expected regret relative to the global mean reward of each arm, defined as the average of that arm's mean rewards across all agents. To this end, we propose a fully distributed algorithm that integrates the arm elimination strategy with the random gossip algorithm. We theoretically show that the regret upper bound is of order $\log T$ and is highly interpretable, where $T$ is the time horizon. It includes the optimal centralized regret $O\left(\sum_{k: Δ_k>0} \frac{\log T}{Δ_k}\right)$ and an additional term $O\left(\frac{N^2 \log T}{p λ_{N-1}(Lap(G))} + \frac{KN^2 \log T}{p}\right)$ where $N$ and $K$ denote the total number of agents and arms, respectively. This term reflects the impact of $G$'s algebraic connectivity $λ_{N-1}(Lap(G))$ and the link probability $p$, and thus highlights a fundamental trade-off between communication efficiency and regret. As a by-product, we show a nearly optimal regret lower bound. Finally, our numerical experiments not only show the superiority of our algorithm over existing benchmarks, but also validate the theoretical regret scaling with problem complexity.

Mengfan Xu, Liren Shan, Fatemeh Ghaffari et al.

We study a novel heterogeneous multi-agent multi-armed bandit problem with a cluster structure induced by stochastic block models, influencing not only graph topology, but also reward heterogeneity. Specifically, agents are distributed on random graphs based on stochastic block models - a generalized Erdos-Renyi model with heterogeneous edge probabilities: agents are grouped into clusters (known or unknown); edge probabilities for agents within the same cluster differ from those across clusters. In addition, the cluster structure in stochastic block model also determines our heterogeneous rewards. Rewards distributions of the same arm vary across agents in different clusters but remain consistent within a cluster, unifying homogeneous and heterogeneous settings and varying degree of heterogeneity, and rewards are independent samples from these distributions. The objective is to minimize system-wide regret across all agents. To address this, we propose a novel algorithm applicable to both known and unknown cluster settings. The algorithm combines an averaging-based consensus approach with a newly introduced information aggregation and weighting technique, resulting in a UCB-type strategy. It accounts for graph randomness, leverages both intra-cluster (homogeneous) and inter-cluster (heterogeneous) information from rewards and graphs, and incorporates cluster detection for unknown cluster settings. We derive optimal instance-dependent regret upper bounds of order $\log{T}$ under sub-Gaussian rewards. Importantly, our regret bounds capture the degree of heterogeneity in the system (an additional layer of complexity), exhibit smaller constants, scale better for large systems, and impose significantly relaxed assumptions on edge probabilities. In contrast, prior works have not accounted for this refined problem complexity, rely on more stringent assumptions, and exhibit limited scalability.

Xingyu Wang, Mengfan Xu

We study decentralized multi-agent multi-armed bandits in fully heavy-tailed settings, where clients communicate over sparse random graphs with heavy-tailed degree distributions and observe heavy-tailed (homogeneous or heterogeneous) reward distributions with potentially infinite variance. The objective is to maximize system performance by pulling the globally optimal arm with the highest global reward mean across all clients. We are the first to address such fully heavy-tailed scenarios, which capture the dynamics and challenges in communication and inference among multiple clients in real-world systems. In homogeneous settings, our algorithmic framework exploits hub-like structures unique to heavy-tailed graphs, allowing clients to aggregate rewards and reduce noises via hub estimators when constructing UCB indices; under $M$ clients and degree distributions with power-law index $α> 1$, our algorithm attains a regret bound (almost) of order $O(M^{1 -\frac{1}α} \log{T})$. Under heterogeneous rewards, clients synchronize by communicating with neighbors, aggregating exchanged estimators in UCB indices; With our newly established information delay bounds on sparse random graphs, we prove a regret bound of $O(M \log{T})$. Our results improve upon existing work, which only address time-invariant connected graphs, or light-tailed dynamics in dense graphs and rewards.

Mengfan Xu, Diego Klabjan

We study a robust, i.e. in presence of malicious participants, multi-agent multi-armed bandit problem where multiple participants are distributed on a fully decentralized blockchain, with the possibility of some being malicious. The rewards of arms are homogeneous among the honest participants, following time-invariant stochastic distributions, which are revealed to the participants only when certain conditions are met to ensure that the coordination mechanism is secure enough. The coordination mechanism's objective is to efficiently ensure the cumulative rewards gained by the honest participants are maximized. To this end, we are the first to incorporate advanced techniques from blockchains, as well as novel mechanisms, into such a cooperative decision making framework to design optimal strategies for honest participants. This framework allows various malicious behaviors and the maintenance of security and participant privacy. More specifically, we select a pool of validators who communicate to all participants, design a new consensus mechanism based on digital signatures for these validators, invent a UCB-based strategy that requires less information from participants through secure multi-party computation, and design the chain-participant interaction and an incentive mechanism to encourage participants' participation. Notably, we are the first to prove the theoretical regret of the proposed algorithm and claim its optimality. Unlike existing work that integrates blockchains with learning problems such as federated learning which mainly focuses on optimality via computational experiments, we demonstrate that the regret of honest participants is upper bounded by $\log{T}$ under certain assumptions. The regret bound is consistent with the multi-agent multi-armed bandit problem, both without malicious participants and with purely Byzantine attacks which do not affect the entire system.

Mengfan Xu, Diego Klabjan

We study the challenging exploration incentive problem in both bandit and reinforcement learning, where the rewards are scale-free and potentially unbounded, driven by real-world scenarios and differing from existing work. Past works in reinforcement learning either assume costly interactions with an environment or propose algorithms finding potentially low quality local maxima. Motivated by EXP-type methods that integrate multiple agents (experts) for exploration in bandits with the assumption that rewards are bounded, we propose new algorithms, namely EXP4.P and EXP4-RL for exploration in the unbounded reward case, and demonstrate their effectiveness in these new settings. Unbounded rewards introduce challenges as the regret cannot be limited by the number of trials, and selecting suboptimal arms may lead to infinite regret. Specifically, we establish EXP4.P's regret upper bounds in both bounded and unbounded linear and stochastic contextual bandits. Surprisingly, we also find that by including one sufficiently competent expert, EXP4.P can achieve global optimality in the linear case. This unbounded reward result is also applicable to a revised version of EXP3.P in the Multi-armed Bandit scenario. In EXP4-RL, we extend EXP4.P from bandit scenarios to reinforcement learning to incentivize exploration by multiple agents, including one high-performing agent, for both efficiency and excellence. This algorithm has been tested on difficult-to-explore games and shows significant improvements in exploration compared to state-of-the-art.