Research map / Bandits and online learning / Online convex optimization and games
Hedging in games: Faster convergence of external and swap regrets
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 Hedge instead of vanilla Hedge | Hedge in two-player games · Two-player games | average regret convergence rate: 1/\sqrt{T} vs. 1/T^{5/6} | Helped |
| Use optimistic Hedge as the regret-minimization component in the Blum-Mansour reduction | Blum-Mansour reduction for swap regret · General m-player games | average swap regret convergence rate: O(m^{1/2}(n\log n/T)^{3/4}) vs. O(1/\sqrt{T}) | Helped |
| Run vanilla Hedge in the repeated-game setting | Hedge in two-player games · Two-action games | regret: \Omega(\sqrt{T}) | Hurt |
Closest papers by meaning
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.89)
- Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games (NeurIPS 2024 · similarity 0.89)
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games (ICLR 2024 · similarity 0.89)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.88)
- On the Universal Near Optimality of Hedge in Combinatorial Settings (NeurIPS 2025 · similarity 0.88)
- Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games (ICLR 2025 · similarity 0.88)
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.