Research map / Bandits and online learning / Online convex optimization and games
Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem
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 the COMB adversary (instead of general adversaries) in the 3-expert finite-time game | 3-expert finite-time prediction game · K=3 finite-time game | minimax regret gap: within 12 log2(T+1) of VT | No clear effect |
| Use COMB-based learner (probability from COMB value differences) instead of MWA | learner for 3-expert game · K=3 finite-time game | regret relative to MWA: MWA regret is 39% larger than the new optimal learner | Helped |
Closest papers by meaning
- Best of Both Worlds: Regret Minimization versus Minimax Play (ICML 2025 · similarity 0.87)
- On Interpolating Experts and Multi-Armed Bandits (ICML 2024 · similarity 0.87)
- Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality (NeurIPS 2025 · similarity 0.86)
- Managing Self-Learning Experts under Per-Round Budget Constraints (NeurIPS 2026 · similarity 0.86)
- On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice (NeurIPS 2024 · similarity 0.86)
- A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds (NeurIPS 2024 · similarity 0.85)
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.