Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Contextual Conservative Interleaving Bandits
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 |
|---|---|---|---|
| Interleaving with baseline actions via GCW (greedy on confidence widths) wrapped around standard bandit algorithms | C2UCB and Thompson sampling · Book-Crossing | per-step regret and performance constraint satisfaction | Helped |
| Using GCW with C2UCB versus standard C2UCB without interleaving | C2UCB · Book-Crossing (fixed and changing actions) | per-step regret | Helped |
| Using the iUCB-style variant Lin-iUCB instead of GCW | Lin-iUCB · Book-Crossing (fixed actions) | performance constraint stability | Hurt |
| GCW wrapped around C2UCB vs GCW wrapped around Thompson sampling | GCW + C2UCB vs GCW + TS · Book-Crossing (fixed and changing actions) | per-step regret | Helped |
| Changing given actions (environment change) with GCW versus baselines | GCW + C2UCB and GCW + TS · Book-Crossing (changing actions) | performance degradation under environment change | Helped |
Closest papers by meaning
- Conservative Contextual Bandits: Beyond Linear Representations (ICLR 2025 · similarity 0.90)
- Feel-Good Thompson Sampling for Contextual Dueling Bandits (ICML 2024 · similarity 0.89)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.89)
- Non-stationary Bandit Convex Optimization: A Comprehensive Study (NeurIPS 2025 · similarity 0.88)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · similarity 0.88)
- Catoni Contextual Bandits are Robust to Heavy-tailed Rewards (ICML 2025 · similarity 0.88)
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.