Yuejie Chi

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers ICLR 2025 Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning ICML 2025 Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization AISTATS 2025 Faster WIND: Accelerating Iterative Best-of-N Distillation for LLM Alignment AISTATS 2025 Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games ICML 2025 Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning ICLR 2025 ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference ICML 2025 The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond JMLR 2025 Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF ICLR 2025 Vertical Federated Learning with Missing Features During Training and Inference ICLR 2025 Accelerating Convergence of Score-Based Diffusion Models, Provably ICML 2024 Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity JMLR 2024 Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression AISTATS 2024 Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization JMLR 2024 Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning NeurIPS 2024 Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices ICML 2024 Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference ICML 2024 In-Context Learning with Representations: Contextual Generalization of Trained Transformers NeurIPS 2024 Learning Discrete Concepts in Latent Hierarchical Models NeurIPS 2024 Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction NeurIPS 2024 Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty ICML 2024 The Sample-Communication Complexity Trade-off in Federated Q-Learning NeurIPS 2024 Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models ICLR 2024 Asynchronous Gradient Play in Zero-Sum Multi-agent Games ICLR 2023 A trajectory is worth three sentences: multimodal transformer for offline reinforcement learning UAI 2023 Counterfactual Generation with Identifiability Guarantees NeurIPS 2023 Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games ICLR 2023 Identification of Nonlinear Latent Hierarchical Models NeurIPS 2023 Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning NeurIPS 2023 Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation NeurIPS 2023 The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond ICML 2023 The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model NeurIPS 2023 The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing ICML 2023 Understanding Masked Autoencoders via Hierarchical Latent Variable Models CVPR 2023 Batch Active Learning with Graph Neural Networks via Multi-Agent Deep Reinforcement Learning AAAI 2022 BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression NeurIPS 2022 Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model NeurIPS 2022 Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity ICML 2022 Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Completion AISTATS 2022 Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements JMLR 2022 SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression NeurIPS 2022 Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent JMLR 2021 Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning NeurIPS 2021 Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization NeurIPS 2021 Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting NeurIPS 2021 Softmax Policy Gradient Methods Can Take Exponential Time to Converge COLT 2021 Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning ICML 2021 Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model NeurIPS 2020 Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction AISTATS 2020 Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction JMLR 2020 Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction NeurIPS 2020 Nonconvex Matrix Factorization from Rank-One Measurements AISTATS 2019 Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion ICML 2018 A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms JMLR 2017 Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow ICML 2016 Spectral Compressed Sensing via Structured Matrix Completion ICML 2013