Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Leveraging Good Representations in Linear Contextual 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 LEADER to select among six representations, including an HLS representation | Linear contextual bandit · Synthetic varying-dimension problem | regret | Helped |
| Combine six representations satisfying mixed-HLS, none individually HLS | Linear contextual bandit · Synthetic representation-mixing problem | regret | Helped |
| Use LEADER instead of model-selection baselines to combine the candidate representations | Linear contextual bandit · Synthetic representation-mixing problem | regret | Helped |
| Use LEADER with all seven learned representations rather than a single representation | Jester ratings bandit · Jester dataset | regret | Helped |
Closest papers by meaning
- Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees (NeurIPS 2022 · similarity 0.93)
- Impact of Representation Learning in Linear Bandits (ICLR 2021 · similarity 0.93)
- Model Selection for Contextual Bandits (NeurIPS 2019 · similarity 0.92)
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits (ICML 2024 · similarity 0.91)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.90)
- Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit (NeurIPS 2024 · 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.