Tianhao Wang

Yifei Min, Tianhao Wang, Ruitu Xu et al.

We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market. At each step, the agents are presented with a dynamical context, where the contexts determine the utilities. The planner controls the transition of the contexts to maximize the cumulative social welfare, while the agents aim to find a myopic stable matching at each step. Such a setting captures a range of applications including ridesharing platforms. We formalize the problem by proposing a reinforcement learning framework that integrates optimistic value iteration with maximum weight matching. The proposed algorithm addresses the coupled challenges of sequential exploration, matching stability, and function approximation. We prove that the algorithm achieves sublinear regret.

Jiafan He, Tianhao Wang, Yifei Min et al.

We study federated contextual linear bandits, where $M$ agents cooperate with each other to solve a global contextual linear bandit problem with the help of a central server. We consider the asynchronous setting, where all agents work independently and the communication between one agent and the server will not trigger other agents' communication. We propose a simple algorithm named \texttt{FedLinUCB} based on the principle of optimism. We prove that the regret of \texttt{FedLinUCB} is bounded by $\tilde{O}(d\sqrt{\sum_{m=1}^M T_m})$ and the communication complexity is $\tilde{O}(dM^2)$, where $d$ is the dimension of the contextual vector and $T_m$ is the total number of interactions with the environment by $m$-th agent. To the best of our knowledge, this is the first provably efficient algorithm that allows fully asynchronous communication for federated contextual linear bandits, while achieving the same regret guarantee as in the single-agent setting.

Runzhe Wang, Sadhika Malladi, Tianhao Wang et al. · tsinghua

Momentum is known to accelerate the convergence of gradient descent in strongly convex settings without stochastic gradient noise. In stochastic optimization, such as training neural networks, folklore suggests that momentum may help deep learning optimization by reducing the variance of the stochastic gradient update, but previous theoretical analyses do not find momentum to offer any provable acceleration. Theoretical results in this paper clarify the role of momentum in stochastic settings where the learning rate is small and gradient noise is the dominant source of instability, suggesting that SGD with and without momentum behave similarly in the short and long time horizons. Experiments show that momentum indeed has limited benefits for both optimization and generalization in practical training regimes where the optimal learning rate is not very large, including small- to medium-batch training from scratch on ImageNet and fine-tuning language models on downstream tasks.

Yan Pang, Aiping Xiong, Yang Zhang et al.

Video generation models (VGMs) have demonstrated the capability to synthesize high-quality output. It is important to understand their potential to produce unsafe content, such as violent or terrifying videos. In this work, we provide a comprehensive understanding of unsafe video generation. First, to confirm the possibility that these models could indeed generate unsafe videos, we choose unsafe content generation prompts collected from 4chan and Lexica, and three open-source SOTA VGMs to generate unsafe videos. After filtering out duplicates and poorly generated content, we created an initial set of 2112 unsafe videos from an original pool of 5607 videos. Through clustering and thematic coding analysis of these generated videos, we identify 5 unsafe video categories: Distorted/Weird, Terrifying, Pornographic, Violent/Bloody, and Political. With IRB approval, we then recruit online participants to help label the generated videos. Based on the annotations submitted by 403 participants, we identified 937 unsafe videos from the initial video set. With the labeled information and the corresponding prompts, we created the first dataset of unsafe videos generated by VGMs. We then study possible defense mechanisms to prevent the generation of unsafe videos. Existing defense methods in image generation focus on filtering either input prompt or output results. We propose a new approach called Latent Variable Defense (LVD), which works within the model's internal sampling process. LVD can achieve 0.90 defense accuracy while reducing time and computing resources by 10x when sampling a large number of unsafe prompts.

Ruitu Xu, Yifei Min, Tianhao Wang et al.

We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market. Each household earns income and engages in consumption at each time step while aiming to maximize a concave utility subject to the underlying market conditions. The households aim to find the optimal saving strategy that maximizes their discounted cumulative utility given the market condition, while the firms determine the market conditions through maximizing corporate profit based on the household population behavior. The model captures a wide range of applications in macroeconomic studies, and we propose a data-driven reinforcement learning framework that finds the regularized competitive equilibrium of the model. The proposed algorithm enjoys theoretical guarantees in converging to the equilibrium of the market at a sub-linear rate.

Zhiyuan Li, Tianhao Wang, JasonD. Lee et al.

As part of the effort to understand implicit bias of gradient descent in overparametrized models, several results have shown how the training trajectory on the overparametrized model can be understood as mirror descent on a different objective. The main result here is a characterization of this phenomenon under a notion termed commuting parametrization, which encompasses all the previous results in this setting. It is shown that gradient flow with any commuting parametrization is equivalent to continuous mirror descent with a related Legendre function. Conversely, continuous mirror descent with any Legendre function can be viewed as gradient flow with a related commuting parametrization. The latter result relies upon Nash's embedding theorem.

Binchi Zhang, Yushun Dong, Tianhao Wang et al.

In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency and strong theoretical guarantees. However, its application to deep neural networks (DNNs), known for their highly nonconvex nature, still poses challenges. To bridge the gap between certified unlearning and DNNs, we propose several simple techniques to extend certified unlearning methods to nonconvex objectives. To reduce the time complexity, we develop an efficient computation method by inverse Hessian approximation without compromising certification guarantees. In addition, we extend our discussion of certification to nonconvergence training and sequential unlearning, considering that real-world users can send unlearning requests at different time points. Extensive experiments on three real-world datasets demonstrate the efficacy of our method and the advantages of certified unlearning in DNNs.

Mingtian Tan, Tianhao Wang, Somesh Jha

Recently, diffusion models (DMs) have become the state-of-the-art method for image synthesis. Editing models based on DMs, known for their high fidelity and precision, have inadvertently introduced new challenges related to image copyright infringement and malicious editing. Our work is the first to formalize and address this issue. After assessing and attempting to enhance traditional image watermarking techniques, we recognize their limitations in this emerging context. In response, we develop a novel technique, RIW (Robust Invisible Watermarking), to embed invisible watermarks leveraging adversarial example techniques. Our technique ensures a high extraction accuracy of $96\%$ for the invisible watermark after editing, compared to the $0\%$ offered by conventional methods. We provide access to our code at https://github.com/BennyTMT/RIW.

James Koch, WoongJo Choi, Ethan King et al.

Lumped parameter methods aim to simplify the evolution of spatially-extended or continuous physical systems to that of a "lumped" element representative of the physical scales of the modeled system. For systems where the definition of a lumped element or its associated physics may be unknown, modeling tasks may be restricted to full-fidelity simulations of the physics of a system. In this work, we consider data-driven modeling tasks with limited point-wise measurements of otherwise continuous systems. We build upon the notion of the Universal Differential Equation (UDE) to construct data-driven models for reducing dynamics to that of a lumped parameter and inferring its properties. The flexibility of UDEs allow for composing various known physical priors suitable for application-specific modeling tasks, including lumped parameter methods. The motivating example for this work is the plunge and dwell stages for friction-stir welding; specifically, (i) mapping power input into the tool to a point-measurement of temperature and (ii) using this learned mapping for process control.

Haoyu Sun, Meng Zhao, Tianhao Wang et al.

Deep learning has shown strong potential for scientific discovery, but its ability to model macroscopic rigid-body kinematic constraints remains underexplored. We study this problem on spatial over-constrained mechanisms and propose O-ConNet, an end-to-end framework that infers mechanism structural parameters from only three sparse reachable points while reconstructing the full motion trajectory, without explicitly solving constraint equations during inference. On a self-constructed Bennett 4R dataset of 42,860 valid samples, O-ConNet achieves Param-MAE 0.276 +/- 0.077 and Traj-MAE 0.145 +/- 0.018 (mean +/- std over 10 runs), outperforming the strongest sequence baseline (LSTM-Seq2Seq) by 65.1 percent and 88.2 percent, respectively. These results suggest that end-to-end learning can capture closed-loop geometric structure and provide a practical route for inverse design of spatial over-constrained mechanisms under extremely sparse observations.

Yan Pang, Wenlong Meng, Xiaojing Liao et al.

With the rapid development of large language models, the potential threat of their malicious use, particularly in generating phishing content, is becoming increasingly prevalent. Leveraging the capabilities of LLMs, malicious users can synthesize phishing emails that are free from spelling mistakes and other easily detectable features. Furthermore, such models can generate topic-specific phishing messages, tailoring content to the target domain and increasing the likelihood of success. Detecting such content remains a significant challenge, as LLM-generated phishing emails often lack clear or distinguishable linguistic features. As a result, most existing semantic-level detection approaches struggle to identify them reliably. While certain LLM-based detection methods have shown promise, they suffer from high computational costs and are constrained by the performance of the underlying language model, making them impractical for large-scale deployment. In this work, we aim to address this issue. We propose Paladin, which embeds trigger-tag associations into vanilla LLM using various insertion strategies, creating them into instrumented LLMs. When an instrumented LLM generates content related to phishing, it will automatically include detectable tags, enabling easier identification. Based on the design on implicit and explicit triggers and tags, we consider four distinct scenarios in our work. We evaluate our method from three key perspectives: stealthiness, effectiveness, and robustness, and compare it with existing baseline methods. Experimental results show that our method outperforms the baselines, achieving over 90% detection accuracy across all scenarios.

Chen Gong, Kecen Li, Jin Yao et al.

Reinforcement learning (RL) trains an agent from experiences interacting with the environment. In scenarios where online interactions are impractical, offline RL, which trains the agent using pre-collected datasets, has become popular. While this new paradigm presents remarkable effectiveness across various real-world domains, like healthcare and energy management, there is a growing demand to enable agents to rapidly and completely eliminate the influence of specific trajectories from both the training dataset and the trained agents. To meet this problem, this paper advocates Trajdeleter, the first practical approach to trajectory unlearning for offline RL agents. The key idea of Trajdeleter is to guide the agent to demonstrate deteriorating performance when it encounters states associated with unlearning trajectories. Simultaneously, it ensures the agent maintains its original performance level when facing other remaining trajectories. Additionally, we introduce Trajauditor, a simple yet efficient method to evaluate whether Trajdeleter successfully eliminates the specific trajectories of influence from the offline RL agent. Extensive experiments conducted on six offline RL algorithms and three tasks demonstrate that Trajdeleter requires only about 1.5% of the time needed for retraining from scratch. It effectively unlearns an average of 94.8% of the targeted trajectories yet still performs well in actual environment interactions after unlearning. The replication package and agent parameters are available online.

Max Lovig, Tianhao Wang, Zhou Fan

Mean-field characterizations of first-order iterative algorithms -- including Approximate Message Passing (AMP), stochastic and proximal gradient descent, and Langevin diffusions -- have enabled a precise understanding of learning dynamics in many statistical applications. For algorithms whose non-linearities have a coordinate-separable form, it is known that such characterizations enjoy a degree of universality with respect to the underlying data distribution. However, mean-field characterizations of non-separable algorithm dynamics have largely remained restricted to i.i.d. Gaussian or rotationally-invariant data. In this work, we initiate a study of universality for non-separable AMP algorithms. We identify a general condition for AMP with polynomial non-linearities, in terms of a Bounded Composition Property (BCP) for their representing tensors, to admit a state evolution that holds universally for matrices with non-Gaussian entries. We then formalize a condition of BCP-approximability for Lipschitz AMP algorithms to enjoy a similar universal guarantee. We demonstrate that many common classes of non-separable non-linearities are BCP-approximable, including local denoisers, spectral denoisers for generic signals, and compositions of separable functions with generic linear maps, implying the universality of state evolution for AMP algorithms employing these non-linearities.

Yifei Min, Jiafan He, Tianhao Wang et al.

We study the stochastic shortest path (SSP) problem in reinforcement learning with linear function approximation, where the transition kernel is represented as a linear mixture of unknown models. We call this class of SSP problems as linear mixture SSPs. We propose a novel algorithm with Hoeffding-type confidence sets for learning the linear mixture SSP, which can attain an $\tilde{\mathcal{O}}(d B_{\star}^{1.5}\sqrt{K/c_{\min}})$ regret. Here $K$ is the number of episodes, $d$ is the dimension of the feature mapping in the mixture model, $B_{\star}$ bounds the expected cumulative cost of the optimal policy, and $c_{\min}>0$ is the lower bound of the cost function. Our algorithm also applies to the case when $c_{\min} = 0$, and an $\tilde{\mathcal{O}}(K^{2/3})$ regret is guaranteed. To the best of our knowledge, this is the first algorithm with a sublinear regret guarantee for learning linear mixture SSP. Moreover, we design a refined Bernstein-type confidence set and propose an improved algorithm, which provably achieves an $\tilde{\mathcal{O}}(d B_{\star}\sqrt{K/c_{\min}})$ regret. In complement to the regret upper bounds, we also prove a lower bound of $Ω(dB_{\star} \sqrt{K})$. Hence, our improved algorithm matches the lower bound up to a $1/\sqrt{c_{\min}}$ factor and poly-logarithmic factors, achieving a near-optimal regret guarantee.

Tianhao Wang, Yu Yang, Ruoxi Jia

The Shapley value (SV) and Least core (LC) are classic methods in cooperative game theory for cost/profit sharing problems. Both methods have recently been proposed as a principled solution for data valuation tasks, i.e., quantifying the contribution of individual datum in machine learning. However, both SV and LC suffer computational challenges due to the need for retraining models on combinatorially many data subsets. In this work, we propose to boost the efficiency in computing Shapley value or Least core by learning to estimate the performance of a learning algorithm on unseen data combinations. Theoretically, we derive bounds relating the error in the predicted learning performance to the approximation error in SV and LC. Empirically, we show that the proposed method can significantly improve the accuracy of SV and LC estimation.

Tianhao Wang, Yi Zeng, Ming Jin et al.

High-quality data is critical to train performant Machine Learning (ML) models, highlighting the importance of Data Quality Management (DQM). Existing DQM schemes often cannot satisfactorily improve ML performance because, by design, they are oblivious to downstream ML tasks. Besides, they cannot handle various data quality issues (especially those caused by adversarial attacks) and have limited applications to only certain types of ML models. Recently, data valuation approaches (e.g., based on the Shapley value) have been leveraged to perform DQM; yet, empirical studies have observed that their performance varies considerably based on the underlying data and training process. In this paper, we propose a task-driven, multi-purpose, model-agnostic DQM framework, DataSifter, which is optimized towards a given downstream ML task, capable of effectively removing data points with various defects, and applicable to diverse models. Specifically, we formulate DQM as an optimization problem and devise a scalable algorithm to solve it. Furthermore, we propose a theoretical framework for comparing the worst-case performance of different DQM strategies. Remarkably, our results show that the popular strategy based on the Shapley value may end up choosing the worst data subset in certain practical scenarios. Our evaluation shows that DataSifter achieves and most often significantly improves the state-of-the-art performance over a wide range of DQM tasks, including backdoor, poison, noisy/mislabel data detection, data summarization, and data debiasing.

Tianhao Wang, Si Chen, Ruoxi Jia

In this work, we initiate the study of one-round active learning, which aims to select a subset of unlabeled data points that achieve the highest model performance after being labeled with only the information from initially labeled data points. The challenge of directly applying existing data selection criteria to the one-round setting is that they are not indicative of model performance when available labeled data is limited. We address the challenge by explicitly modeling the dependence of model performance on the dataset. Specifically, we propose DULO, a data-driven framework for one-round active learning, wherein we learn a model to predict the model performance for a given dataset and then leverage this model to guide the selection of unlabeled data. Our results demonstrate that DULO leads to the state-of-the-art performance on various active learning benchmarks in the one-round setting.

Tianhao Wang, Dongruo Zhou, Quanquan Gu

We study reinforcement learning (RL) with linear function approximation under the adaptivity constraint. We consider two popular limited adaptivity models: the batch learning model and the rare policy switch model, and propose two efficient online RL algorithms for episodic linear Markov decision processes, where the transition probability and the reward function can be represented as a linear function of some known feature mapping. In specific, for the batch learning model, our proposed LSVI-UCB-Batch algorithm achieves an $\tilde O(\sqrt{d^3H^3T} + dHT/B)$ regret, where $d$ is the dimension of the feature mapping, $H$ is the episode length, $T$ is the number of interactions and $B$ is the number of batches. Our result suggests that it suffices to use only $\sqrt{T/dH}$ batches to obtain $\tilde O(\sqrt{d^3H^3T})$ regret. For the rare policy switch model, our proposed LSVI-UCB-RareSwitch algorithm enjoys an $\tilde O(\sqrt{d^3H^3T[1+T/(dH)]^{dH/B}})$ regret, which implies that $dH\log T$ policy switches suffice to obtain the $\tilde O(\sqrt{d^3H^3T})$ regret. Our algorithms achieve the same regret as the LSVI-UCB algorithm (Jin et al., 2019), yet with a substantially smaller amount of adaptivity. We also establish a lower bound for the batch learning model, which suggests that the dependency on $B$ in our regret bound is tight.

Tianhao Wang, Florian Kerschbaum

Watermarking of deep neural networks (DNN) can enable their tracing once released by a data owner. In this paper, we generalize white-box watermarking algorithms for DNNs, where the data owner needs white-box access to the model to extract the watermark. White-box watermarking algorithms have the advantage that they do not impact the accuracy of the watermarked model. We propose Robust whIte-box GAn watermarking (RIGA), a novel white-box watermarking algorithm that uses adversarial training. Our extensive experiments demonstrate that the proposed watermarking algorithm not only does not impact accuracy, but also significantly improves the covertness and robustness over the current state-of-art.