Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Stage-wise Conservative Linear 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 |
|---|---|---|---|
| use larger conservatism fraction alpha | SCLTS · Synthetic linear bandit, T=10000 | average regret | Helped |
| SCLTS/SCLUCB randomized exploration instead of SEGE greedy baseline-reliant exploration | stage-wise conservative linear bandit · Synthetic linear bandit, alpha=0.2 | cumulative regret | Helped |
Closest papers by meaning
- Feasible Action Search for Bandit Linear Programs via Thompson Sampling (ICML 2025 · similarity 0.91)
- Conservative Contextual Bandits: Beyond Linear Representations (ICLR 2025 · similarity 0.91)
- Constrained Linear Thompson Sampling (NeurIPS 2025 · similarity 0.90)
- Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards (NeurIPS 2025 · similarity 0.90)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.89)
- Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits (ICLR 2025 · similarity 0.89)
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.