Minshuo Chen

Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data ICLR 2025 On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality ICLR 2025 A Theoretical Perspective for Speculative Decoding Algorithm NeurIPS 2024 Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces JMLR 2024 Gradient Guidance for Diffusion Models: An Optimization Perspective NeurIPS 2024 Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks NeurIPS 2024 Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis AISTATS 2024 Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds JMLR 2024 Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight ICLR 2024 Theoretical insights for diffusion guidance: A case study for Gaussian mixture models ICML 2024 Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling ICML 2024 Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning ICLR 2023 Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories ICML 2023 Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations NeurIPS 2023 Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement NeurIPS 2023 Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks ICLR 2023 Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data ICML 2023 Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint ICML 2022 Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect ICLR 2022 On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds NeurIPS 2022 Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks ICML 2021 How Important is the Train-Validation Split in Meta-Learning? ICML 2021 Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL NeurIPS 2021 Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization ACL 2021 Differentiable Top-k with Optimal Transport NeurIPS 2020 On Computation and Generalization of Generative Adversarial Imitation Learning ICLR 2020 On Generalization Bounds of a Family of Recurrent Neural Networks AISTATS 2020 Towards Understanding Hierarchical Learning: Benefits of Neural Representations NeurIPS 2020 Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds NeurIPS 2019 On Computation and Generalization of Generative Adversarial Networks under Spectrum Control ICLR 2019 On Scalable and Efficient Computation of Large Scale Optimal Transport ICML 2019 Towards Understanding the Importance of Shortcut Connections in Residual Networks NeurIPS 2019 Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization NeurIPS 2018