Research map / Bandits and online learning / Online convex optimization and games
Constant Regret, Generalized Mixability, and Mirror Descent
Zakaria Mhammedi, Robert C. Williamson
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 |
|---|---|---|---|
| Add average-loss correction vectors to the AGAA update | AGAA with Shannon entropy · Brier game, 2 experts, T ≥ 150 | regret bound: R^{Φ}_{ℓ_{Brier}} + ΔR_{θ*}(T) ≃ -5 | Improved |
| Use the AA instead of the AGAA with correction vectors | Brier game, 2 experts · Brier game, 2 experts, T ≥ 150 | regret: ≃ R^{S}_{ℓ_{Brier}} = log 2 | Hurt |
| Use the AGAA rather than the AA | Football game prediction datasets · Football game predictions | regret | Improved |
| Use Shannon entropy rather than another admissible entropy | Generalized Aggregating Algorithm · Prediction with expert advice | worst-case regret bound | Improved |
Closest papers by meaning
- Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability (ICML 2025 · similarity 0.87)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.85)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.85)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.85)
- When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses (NeurIPS 2025 · similarity 0.85)
- The Relationship Between No-Regret Learning and Online Conformal Prediction (ICML 2025 · 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.
