Research map / Bandits and online learning / Online convex optimization and games
On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds
David Woodruff, Fred Zhang, Samson Zhou
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 randomized pool-sampling algorithm instead of the deterministic pool algorithm against a white-box adversary | Experts algorithm with pools of k experts · Synthetic white-box adversary, n=100000 | number of mistakes: 1.98x to 3.29x more mistakes | Hurt |
| Vary target regret R from 0.05 to 0.35 | Deterministic and randomized pool algorithms · n=10000, M=20, T=1000 | number of mistakes | No clear effect |
| Increase T tenfold (1000 to 10000) and lower M to 10 | Randomized pool algorithm · n=100000 | mistake ratio vs deterministic: 1.98x -> 3.06x | Hurt |
Closest papers by meaning
- Equipping Experts/Bandits with Long-term Memory (NeurIPS 2019 · similarity 0.88)
- When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses (NeurIPS 2025 · similarity 0.88)
- No-Regret Online Prediction with Strategic Experts (NeurIPS 2023 · similarity 0.88)
- Managing Self-Learning Experts under Per-Round Budget Constraints (NeurIPS 2026 · similarity 0.87)
- Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making (NeurIPS 2025 · similarity 0.86)
- Online Learning with Unknown Constraints (ICML 2025 · similarity 0.86)
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.
