Research map / Bandits and online learning / Online convex optimization and games
Bounding Regret in Empirical Games
Steven Jecmen, Arunesh Sinha, Zun Li, Long Tran-Thanh
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 SAUCB (derivative-guided arm sampling) instead of naive uniform sampling | regret bounding in empirical games · Synthetic Exp. A, B, C (20 Bernoulli arms) | bound width over samples | Improved |
| use SAUCB instead of COCI | regret bounding in empirical games · Synthetic Exp. A, B, C | bound width | Improved |
| use SAUCB instead of Modified SE | regret bounding in empirical games · Synthetic Exp. A, B, C | bound width | Improved |
| sample within super-arm by derivative values rather than uniformly (UAS) (ablation) | SAUCB · Exp. A (all arms in support) | bound width | Improved |
| sample within super-arm by derivative values rather than uniformly (UAS) (ablation) | SAUCB · Exp. B and C | bound width | Mixed |
| use SAUCB versus baselines | regret bounding in empirical games · Synthetic Exp. A, B, C | probability of correct bound | Improved |
| use Hoeffding bounds versus lil bound in SAUCB (lil-SAUCB variant) (ablation) | SAUCB · Exp. A, B, C | samples to reach bound width | Improved |
| use super-arm-wide sampling versus single-SAUCB variant (ablation) | SAUCB · Exp. A, B, C | samples to reach bound width | Improved |
| use SAUCB versus baselines on stock-market empirical game | regret bounding · LSHN-K0 and MSMN-K0 | samples to reach width W=0.1 | Improved |
Closest papers by meaning
- Fairness and Welfare Quantification for Regret in Multi-Armed Bandits (AAAI 2023 · similarity 0.90)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.89)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.88)
- Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games (NeurIPS 2024 · similarity 0.88)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.88)
- Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting (NeurIPS 2024 · 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.
