Research map / Bandits and online learning / Online convex optimization and games
Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum 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 Dual Averaging without assuming convexity of the action set or rewards | Online optimization on compact metric spaces · Convex quadratics on hypercube, n=2 and n=3 | simulation regret decay rate: -0.519 (n=2), -0.481 (n=3) for DA, Exp; OGD: -0.920 (n=2), -0.892 (n=3) | Mixed |
| Use 1.5-Norm instead of exponential potential (ablation) | Dual Averaging · Convex quadratics on hypercube | simulation regret decay rate: -0.557 -> -0.307 | Mixed |
| Use 1.75-Norm rather than 1.5-Norm potential (ablation) | Dual Averaging · Convex quadratics on hypercube | simulation regret decay rate: -0.307 -> -0.279 | Hurt |
| Use 1.05-Norm rather than 1.01-Norm potential (ablation) | Dual Averaging · Convex quadratics on hypercube | simulation regret decay rate: -0.546 -> -0.477 | Hurt |
Closest papers by meaning
- Best of Both Worlds: Regret Minimization versus Minimax Play (ICML 2025 · similarity 0.92)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.92)
- Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes (NeurIPS 2019 · similarity 0.92)
- Regret Minimization and Convergence to Equilibria in General-sum Markov Games (ICML 2023 · similarity 0.92)
- Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games (ICML 2019 · similarity 0.91)
- 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.