Profiles2022-2026
Weiqiang Zheng
Yale University
15Papers
13Last author
16Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General PreferencesAuthor 3 of 5ICLR 2026 · 5 citations
- Proximal Regret and Proximal Correlated Equilibria: A New Tractable Solution Concept for Online Learning and GamesAuthor 5 of 5STOC 2026 · 5 citations
- Fisher Meets Lindahl: A Unified Duality Framework for Market EquilibriumAuthor 2 of 2STOC 2026 · 2 citations
- Asymptotic Universal Alignment: A New Alignment Framework via Test-Time ScalingAuthor 2 of 2ICML 2026
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its ApplicationsAuthor 4 of 4NeurIPS 2025 · 9 citations
- Last-Iterate Convergence Properties of Regret-Matching Algorithms in GamesAuthor 6 of 6ICLR 2025
- Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone InclusionAuthor 3 of 3ICML 2024 · 26 citations
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful AlgorithmsAuthor 6 of 6NeurIPS 2024 · 24 citations
- Learning Thresholds with Latent Values and Censored FeedbackAuthor 3 of 6ICLR 2024 · 2 citations
- On Tractable Φ-Equilibria in Non-Concave GamesAuthor 5 of 5NeurIPS 2024
- Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit FeedbackAuthor 4 of 4NeurIPS 2023 · 31 citations
- Doubly Optimal No-Regret Learning in Monotone GamesAuthor 2 of 2ICML 2023 · 23 citations
- Accelerated Single-Call Methods for Constrained Min-Max OptimizationAuthor 2 of 2ICLR 2023 · 3 citations
- Finite-Time Last-Iterate Convergence for Learning in Multi-Player GamesAuthor 3 of 3NeurIPS 2022 · 63 citations
- Nash Convergence of Mean-Based Learning Algorithms in First Price AuctionsAuthor 4 of 4WWW 2022 · 16 citations
