Research map / Bandits and online learning / Online convex optimization and games
Tight last-iterate convergence rates for no-regret learning in multi-player games
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use optimistic gradient with a constant step size and adaptive potential functions | Learning in smooth monotone games · Smooth monotone games | gradient gap convergence rate: O(1/\sqrt{T}) | Helped |
| Use optimistic gradient with a constant step size | Learning in smooth monotone games · Smooth monotone games | total gap convergence rate: \frac{180 KD^2}{\eta \sqrt{T}} | Helped |
| Restrict the algorithm to the p-SCLI class | Last-iterate methods for monotone games · Bilinear games | total gap convergence rate: \frac{c_\MA \ell D^2}{\sqrt{T}} | Hurt |
| Implement extragradient using alternating online actions | Online multi-agent learning · Adversarial losses | regret: \Omega(T) | Hurt |
Closest papers by meaning
- Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games (ICLR 2025 · similarity 0.92)
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions (NeurIPS 2026 · similarity 0.91)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.91)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.91)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.90)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.