Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Context-lumpable stochastic 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 |
|---|---|---|---|
| Exploit shared reward rows across unknown context groups rather than learn each context-action pair independently | Context-lumpable bandits · PAC policy learning | sample complexity: \widetilde O(SK/\varepsilon^2) -> \widetilde O(r(S+K)/\varepsilon^2) | Helped |
| Exploit context lumpability using phased elimination and clustering | Context-lumpable bandits · Online regret minimization | cumulative regret: \widetilde O(\sqrt{SKT}) -> \widetilde O(\sqrt{r^3(S+K)T}) | Helped |
| Use the proposed PAC algorithm under the context-lumpability assumption | Context-lumpable bandits · PAC policy learning | sample complexity: \widetilde O(r(S+K)/\varepsilon^2); \Omega(r(S+K)/\varepsilon^2) | No clear effect |
| Use different data-collection lengths for accuracy levels and maintain good-action sets at each level | Proposed online algorithm · Non-uniform block distribution | cumulative regret: \widetilde O(\sqrt{r^3(S+K)T}) | Helped |
Closest papers by meaning
- Stochastic Bandits with Context Distributions (NeurIPS 2019 · similarity 0.93)
- Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces (ICML 2022 · similarity 0.92)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.92)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (NeurIPS 2024 · similarity 0.91)
- Contextual Bandits for Unbounded Context Distributions (ICML 2025 · similarity 0.90)
- From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards (NeurIPS 2025 · similarity 0.90)
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.