Profiles2022-2025
Jincheng Mei
Google Research, Brain Team
6Papers
0Last author
9Unique co-authors
4First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers6
- REINFORCE Converges to Optimal Policies with Any Learning RateAuthor 6 of 7NeurIPS 2025 · 2 citations
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning ratesAuthor 1 of 6NeurIPS 2024 · 5 citations
- Stochastic Gradient Succeeds for BanditsAuthor 1 of 7ICML 2023 · 6 citations
- Ordering-based Conditions for Global Convergence of Policy Gradient MethodsAuthor 1 of 6NeurIPS 2023 · 4 citations
- On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential GamesAuthor 2 of 5NeurIPS 2022 · 38 citations
- The Role of Baselines in Policy Gradient OptimizationAuthor 1 of 6NeurIPS 2022 · 34 citations
