Research map / Bandits and online learning / Online convex optimization and games
Improved Regret Bounds for Tracking Experts with Memory
James Robinson, Mark Herbster
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 |
|---|---|---|---|
| Replace the Markov-prior partition specialists update with PoDS-theta / Share-theta (geometric-decay mixing) | Tracking experts with memory · Regret bound, n=500000, k=40, T=4000 | regret bound | Improved |
| Use memory-based PoDS-theta instead of Fixed-Share when comparison sequence has few unique experts | Fixed-Share · Regret bound with m unique experts | regret bound | Improved |
| Set theta to 0 when m = k+1 (no useful memory) (ablation) | PoDS-theta / Share-theta · Regret bound | regret bound | No clear effect |
| Replace weight-sharing update with relative entropy projection onto dynamic set | Generalized share update · Update cost (1-norm weight change) | weight update cost | Improved |
| Pay the switching cost once per switch plus a smaller cost per remembered expert, instead of twice per switch | Previous best memory bound · Regret bound | regret bound | Improved |
Closest papers by meaning
- When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses (NeurIPS 2025 · similarity 0.88)
- Tracking The Best Expert Privately (ICML 2025 · similarity 0.87)
- A second order regret bound for NormalHedge (NeurIPS 2026 · similarity 0.86)
- Managing Self-Learning Experts under Per-Round Budget Constraints (NeurIPS 2026 · similarity 0.86)
- Non-stationary Bandit Convex Optimization: A Comprehensive Study (NeurIPS 2025 · similarity 0.85)
- On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning (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.
