Scholar
Jincheng Mei
Google Scholar ID: g2uX6_gAAAAJ
Research Scientist, Google DeepMind
Citations & Impact
Citations
1,023
H-index
16
i10-index
18
Publications
20
Co-authors
15
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- REINFORCE Converges to Optimal Policies with Any Learning Rate (NeurIPS, 2025)
- Faster WIND: Accelerating Iterative Best-of-N Distillation for LLM Alignment (AISTATS, 2025)
- Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF (ICLR, 2025)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS, 2024)
- Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation (ICML, 2024, Spotlight)
- Ordering-based Conditions for Global Convergence of Policy Gradient Methods (NeurIPS, 2023, Oral Presentation)
- Stochastic Gradient Succeeds for Bandits (ICML, 2023)
- Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice (ICML, 2023)
- The Role of Baselines in Policy Gradient Optimization (NeurIPS, 2022)
- On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games (NeurIPS, 2022)
- KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal (partial information)
Research Experience
- Interned at Google Brain (Aug. 2019 - Aug. 2021) and Borealis AI (Sep. 2018 - Jan. 2019 and Mar. 2019 - May 2019).
Education
- Ph.D. in Statistical Machine Learning from the University of Alberta (Sep. 2015 - Sep. 2021), supervised by Dale Schuurmans; M.S. from Shanghai Jiao Tong University (Mar. 2015), supervised by Bao-Liang Lu; B.E. from South China University of Technology (June 2012).
Background
- Research interests include machine learning, reinforcement learning, and optimization. Currently a senior research scientist at Google DeepMind (previously at Google Brain Canada until April 20, 2023).
