Jincheng Mei

Identifiers

• name variant Jincheng Mei 0.60 · backfill

Papers (20)

1. Delightful Gradients Accelerate Corner Escape cs.LG · 2026 · author #1
2. Revisiting Mixture Policies in Entropy-Regularized Actor-Critic cs.LG · 2026 · author #3
3. Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation cs.LG · 2025 · author #2
4. Ordering-based Conditions for Global Convergence of Policy Gradient Methods cs.LG · 2025 · author #1
5. Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates cs.LG · 2025 · author #1
6. Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment cs.LG · 2024 · author #2
7. Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF cs.LG · 2024 · author #2
8. Stochastic Gradient Succeeds for Bandits cs.LG · 2024 · author #1
9. Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice cs.LG · 2023 · author #7
10. The Role of Baselines in Policy Gradient Optimization cs.LG · 2023 · author #1
11. KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal cs.LG · 2022 · author #6
12. On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games math.OC · 2022 · author #2
13. Understanding the Effect of Stochasticity in Policy Optimization cs.LG · 2021 · author #1
14. Leveraging Non-uniformity in First-order Non-convex Optimization cs.LG · 2021 · author #1
15. On the Optimality of Batch Policy Optimization Algorithms cs.LG · 2021 · author #5
16. Understanding and Mitigating the Limitations of Prioritized Experience Replay cs.AI · 2020 · author #2
17. On the Global Convergence Rates of Softmax Policy Gradient Methods cs.LG · 2020 · author #1
18. Frequency-based Search-control in Dyna cs.LG · 2020 · author #2
19. On the Reducibility of Submodular Functions cs.LG · 2016 · author #1
20. On Unconstrained Quasi-Submodular Function Optimization cs.DS · 2014 · author #1

Mentions

• 2505.03155 #2 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2504.02130 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2410.20727 #2 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2405.19320 #2 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2502.07141 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2402.17235 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2305.13185 #7 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2301.06276 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2202.00872 #2 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2007.09569 #2 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2105.06072 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2005.06392 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2205.14211 #6 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2110.15572 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2104.02293 #5 · arxiv_oai · confidence 0.70 Jincheng Mei
• 2002.05822 #2 · arxiv_oai · confidence 0.70 Jincheng Mei
• 1601.00393 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 1408.4389 #1 · arxiv_oai · confidence 0.70 Jincheng Mei
• 1408.4389 #1 · backfill · confidence 0.70 Jincheng Mei

Frequent Coauthors

• Dale Schuurmans 12 shared papers
• Bo Dai 11 shared papers
• Csaba Szepesvari 9 shared papers
• Alekh Agarwal 4 shared papers
• Chenjun Xiao 3 shared papers
• Amir-massoud Farahmand 2 shared papers
• Bao-Liang Lu 2 shared papers
• Csaba Szepesv\'ari 2 shared papers
• Hanjun Dai 2 shared papers
• Martha White 2 shared papers
• Matthieu Geist 2 shared papers
• Michal Valko 2 shared papers
• Mohammad Gheshlaghi Azar 2 shared papers
• Nino Vieillard 2 shared papers
• Olivier Pietquin 2 shared papers
• Pierre M\'enard 2 shared papers
• R\'emi Munos 2 shared papers
• Sharan Vaswani 2 shared papers
• Shicong Cen 2 shared papers
• Tadashi Kozuno 2 shared papers