Publications

Preprints

1. Training-Free Adaptation of Diffusion Models via Doob's h-Transform
   Qijie Zhu, Zeqi Ye, Han Liu, Zhaoran Wang, and Minshuo Chen
   

2. Diffusion Factor Models: Generating High-Dimensional Returns with Factor Structure
   Minshuo Chen, Renyuan Xu, Yumin Xu, and Ruixun Zhang
   Short version accepted at Vienna Congress on Mathematical Finance (VCMF 2025)
   SIAM Financial Mathematics and Engineering Conference Best Paper Prize
   Runner-up of the 2025 INFORMS Best Student Paper Competition in Finance
   Reject and resubmit, Operations Research
   

3. Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
   Hengyu Fu, Zhuoran Yang, Mengdi Wang, and Minshuo Chen
   

4. Doubly Robust Off-Policy Learning on Low-Dimensional Manifolds by Deep Neural Networks
   Minshuo Chen, Hao Liu, Wenjing Liao, and Tuo Zhao
   Minor revision at Mathematics of Operations Research
   

5. Distribution Approximation and Statistical Estimation Guarantees of Generative Adversarial Networks
   Minshuo Chen, Wenjing Liao, Hongyuan Zha, and Tuo Zhao
   

Journal Papers

1. Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds
   Zhenghao Xu, Xiang Ji, Minshuo Chen, Mengdi Wang, and Tuo Zhao
   Journal of Machine Learning Research, 2024
   

2. Challenges and Opportunities of Diffusion Models for Generative AI: Applications, Guided Generation, Statistical Rates and Optimization
   Minshuo Chen, Song Mei, Jianqing Fan, and Mengdi Wang
   National Science Review, 2024
   

3. Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
   Minshuo Chen, Jie Meng, Yu Bai, Yinyu Ye, H. Vincent Poor, and Mengdi Wang
   IEEE Transactions on Information Theory, 2024
   

4. Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces
   Hao Liu, Haizhao Yang, Minshuo Chen, Tuo Zhao, and Wenjing Liao
   Journal of Machine Learning Research, 2024
   

5. High Dimensional Binary Classification under Label Shift: Phase Transition and Regularization
   Jiahui Cheng, Minshuo Chen, Hao Liu, Tuo Zhao, Wenjing Liao
   Sampling Theory, Signal Processing, and Data Analysis, 2023
   

6. A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networks
   Jie Wang, Minshuo Chen, Tuo Zhao, Wenjing Liao, Yao Xie
   IMA, Information and Inference, 2023
   

7. Nonparametric Regression on Low-Dimensional Manifolds using Deep ReLU Networks : Function Approximation and Statistical Recovery
   Minshuo Chen, Haoming Jiang, Wenjing Liao, and Tuo Zhao
   IMA, Information and Inference, 2022
   

Conference Papers

1. Provable separations between memorization and generalization in diffusion models
   Zeqi Ye, Qijie Zhu, Molei Tao, and Minshuo Chen
   International Conference on Learning Representations (ICLR), 2026
   

2. Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
   Zeqi Ye, Minshuo Chen
   Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
   

3. Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
   Hengyu Fu, Zehao Dou, Jiawei Guo, Mengdi Wang, and Minshuo Chen
   International Conference on Learning Representations (ICLR), 2025
   

4. A Theoretical Perspective for Speculative Decoding Algorithm
   Ming Yin, Minshuo Chen, Kaixuan Huang, and Mengdi Wang
   Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
   

5. Gradient Guidance for Diffusion Models: An Optimization Perspective
   Yingqing Guo, Hui Yuan, Yukang Yang, Minshuo Chen, and Mengdi Wang
   Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
   

6. Provable Statistical Rates for Consistency Diffusion Models
   Zehao Dou, Minshuo Chen, Mengdi Wang, and Zhuoran Yang
   International Conference on Machine Learning (ICML), 2024
   

7. Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
   Yuchen Wu, Minshuo Chen, Zihao Li, Mengdi Wang, and Yuting Wei
   International Conference on Machine Learning (ICML), 2024
   

8. Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
   Jiacheng Guo, Minshuo Chen, Huan Wang, Caiming Xiong, Mengdi Wang, and Yu Bai
   International Conference on Learning Representations (ICLR), 2024
   

9. Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
   Hui Yuan, Kaixuan Huang, Chengzhuo Ni, Minshuo Chen, and Mengdi Wang
   Annual Conference on Neural Information Processing Systems (NeurIPS), 2023
   

10. Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
    Minshuo Chen, Jie Meng, Yu Bai, Yinyu Ye, H. Vincent Poor, and Mengdi Wang
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2023
    

11. Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
    Minshuo Chen*, Kaixuan Huang*, Tuo Zhao, and Mengdi Wang (* Equal Contribution)
    International Conference on Machine Learning (ICML), 2023
    

12. Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories
    Zixuan Zhang, Minshuo Chen, Mengdi Wang, Wenjing Liao, and Tuo Zhao
    International Conference on Machine Learning (ICML), 2023
    

13. Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
    Qingru Zhang, Minshuo Chen, Alexander Bukharin, Pengcheng He, Yu Cheng, Weizhu Chen, and Tuo Zhao
    International Conference on Learning Representations (ICLR), 2023
    

14. Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks
    Xiang Ji, Minshuo Chen, Mengdi Wang, and Tuo Zhao
    International Conference on Learning Representations (ICLR), 2023
    

15. On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds
    Biraj Dahal, Alex Havrilla, Minshuo Chen, Tuo Zhao, and Wenjing Liao
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2022
    

16. Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
    Hao Liu, Minshuo Chen, Siawpeng Er, Wenjing Liao, Tong Zhang, and Tuo Zhao
    International Conference on Machine Learning (ICML), 2022
    

17. Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect
    Yuqing Wang, Minshuo Chen, Tuo Zhao, and Molei Tao
    International Conference on Learning Representations (ICLR), 2022
    

18. Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL
    Minshuo Chen, Yan Li, Ethan Wang, Zhuoran Yang, Zhaoran Wang, and Tuo Zhao
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2021
    

19. How Important is the Train-Validation Split in Meta-Learning
    Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, and Caiming Xiong
    International Conference on Machine Learning (ICML), 2021
    

20. Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
    Hao Liu, Minshuo Chen, Tuo Zhao, and Wenjing Liao
    International Conference on Machine Learning (ICML), 2021
    

21. Towards Understanding Hierarchical Learning: Benefits of Neural Representations
    Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, and Richard Socher
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2020
    

22. Differentiable Top-k Operator with Optimal Transport
    Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2020
    

23. On Generalization Bounds of a Family of Recurrent Neural Networks
    Minshuo Chen, Xingguo Li, and Tuo Zhao
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2020

24. On Computation and Generalization of Generative Adversarial Imitation Learning
    Minshuo Chen, Yizhou Wang, Tianyi Liu, Zhuoran Yang, Xingguo Li, Zhaoran Wang, and Tuo Zhao
    International Conference on Learning Representations (ICLR), 2020

25. Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
    Minshuo Chen, Haoming Jiang, Wenjing Liao, and Tuo Zhao (Alphabetical Order)
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2019

26. Towards Understanding the Importance of Shortcut Connections in Residual Networks
    Tianyi Liu*, Minshuo Chen*, Mo Zhou, Simon Du, Enlu Zhou, and Tuo Zhao (* Equal Contribution)
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2019

27. On Scalable and Efficient Computation of Large Scale Optimal Transport
    Yujia Xie, Minshuo Chen, Haoming Jiang, Tuo Zhao, and Hongyuan Zha
    International Conference on Machine Learning (ICML), 2019

28. On Computation and Generalization of Generative Adversarial Networks under Spectrum Control
    Haoming Jiang, Zhehui Chen, Minshuo Chen, Feng Liu, Dingding Wang, and Tuo Zhao
    International Conference on Learning Representations (ICLR), 2019

29. Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization
    Minshuo Chen, Lin Yang, Mengdi Wang, and Tuo Zhao
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2018