Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Contextual Recommendations and Low-Regret Cutting-Plane Algorithms
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 |
|---|---|---|---|
| Query the center of gravity of the knowledge set expanded by (1/T)B | Strong separation oracle · Contextual recommendation | regret: O(d log T) | Helped |
| Query the center of the John ellipsoid of the knowledge set | Strong separation oracle · Contextual recommendation | regret: exp(O(d log d)) | Helped |
| Randomly query a point from a d^4-piece curvature-path discretization | Weak separation oracle · Weak separation oracle | expected cutting-plane regret: O(d^5 log^2 d) | Helped |
| Recommend best responses to points in a curvature-path discretization | List contextual recommendation · List contextual recommendation | regret: O(d^2 log d) | Helped |
| Add H - 1 uniformly sampled actions to the action determined by the cutting-plane query | Local contextual recommendation · Local contextual recommendation | regret: O(ρ · A / (H - 1)) | Helped |
| Allow lists as large as 2^{Ω(d)} | Any local contextual recommendation algorithm · Local contextual recommendation | regret lower bound: 2^{Ω(d)} | Hurt |
Closest papers by meaning
- Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness (NeurIPS 2026 · similarity 0.89)
- Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation (NeurIPS 2026 · similarity 0.89)
- From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards (NeurIPS 2025 · similarity 0.88)
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (NeurIPS 2025 · similarity 0.88)
- Regret minimization in Linear Bandits with offline data via extended D-optimal exploration. (NeurIPS 2026 · similarity 0.88)
- On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice (NeurIPS 2024 · similarity 0.87)
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.