Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
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 |
|---|---|---|---|
| replace smoothness with TPVM condition | BCUCB-T · Disjunctive cascading bandits | regret bound | Helped |
| replace smoothness with TPVM condition | BCUCB-T · Conjunctive cascading bandits | regret bound | Helped |
| replace smoothness with TPVM condition | BCUCB-T · MuLaNE | regret bound | Helped |
| replace smoothness with TPVM condition | BCUCB-T · OIM on DAG | regret bound | Helped |
| use VM condition with efficient SESCB for independent arms | SESCB · Probabilistic maximum coverage | regret bound: O(log2 k) | Helped |
Closest papers by meaning
- Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications (NeurIPS 2017 · similarity 0.93)
- Thompson Sampling for Combinatorial Semi-Bandits (ICML 2018 · similarity 0.91)
- Offline Learning for Combinatorial Multi-armed Bandits (ICML 2025 · similarity 0.89)
- Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond (ICML 2024 · similarity 0.88)
- Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation (NeurIPS 2026 · similarity 0.88)
- Combinatorial Stochastic-Greedy Bandit (AAAI 2024 · 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.