Research map / Bandits and online learning / Online convex optimization and games
Optimistic Bandit Convex Optimization
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 |
|---|---|---|---|
| predict the next round's averaged smoothed gradient (optimistic FTRL, predicting re-used information) | BCO with averaged smoothed gradients (Lipschitz losses) · Lipschitz loss BCO | regret exponent in T: T^{11/16} vs prior T^{5/6}/T^{3/4} | Helped |
| predict the next round's averaged smoothed gradient (optimistic FTRL) | BCO with Lipschitz gradients · C1,1 loss BCO | regret exponent in T: T^{8/13} vs T^{5/8} (Dekel et al.) | Helped |
| predicting the predictable part of averaged gradient yields a 1/(k+1)^2 factor instead of 1/(k+1) | OptimisticBCO analysis · Lipschitz loss BCO | regret term | Helped |
Closest papers by meaning
- Improved Regret for Bandit Convex Optimization with Delayed Feedback (NeurIPS 2024 · similarity 0.92)
- Non-stationary Bandit Convex Optimization: A Comprehensive Study (NeurIPS 2025 · similarity 0.90)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.90)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Nearly Minimax Optimal Submodular Maximization with Bandit Feedback (NeurIPS 2024 · similarity 0.89)
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.