Research

My research interests include stochastic control, reinforcement learning, nonconvex and stochastic optimization, diffusion models and applications in management and finance.

Working Papers and Preprints

• Yinbin Han and Meisam Razaviyayn. Inexact Moreau Envelope Augmented Lagrangian Method for Nonconvex Robust Constrained Optimization. Preprint, 2025.
  • Short version accepted by NeurIPS Workshop on Constrained Optimization for Machine Learning, 2025.
• Haoyang Cao, Minshuo Chen, Yinbin Han, and Renyuan Xu. Diffusion Models for Adapted Sequential Data Generation. Preprint, 2025.
  • Short version accepted by NeurIPS Workshop MLxOR, 2025.

Conference Proceedings

• Yinbin Han, Meisam Razaviyayn, and Renyuan Xu. Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity and Convergence. International Conference on Machine Learning (ICML), 2025.

• Yinbin Han, Meisam Razaviyayn, and Renyuan Xu. Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization. International Conference on Learning Representations (ICLR), 2024.

  • Short version accepted by NeurIPS Workshop on Diffusion Models, 2023.

Journal Publications

• Yinbin Han, Meisam Razaviyayn, and Renyuan Xu. Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators. SIAM Journal on Control and Optimization, 2025.
  • Short version accepted by NeurIPS Workshop Optimization for Machine Learning, 2022.
• Yinbin Han and Zizhuo Wang. Optimal Switching Policy for Batch Servers. Operations Research Letters, 2023.