Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Factored 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 |
|---|---|---|---|
| Apply TEA to utility-based dueling bandits instead of the state-of-the-art algorithms discussed | Utility-based dueling bandits · Utility-based dueling bandits | additive factor in regret bound: reduced by a multiplicative factor of K | Helped |
| Use Dueling Bandit TEA rather than baseline algorithms | Utility-based dueling bandits · Utility-based dueling bandits, sufficiently large K | regret | Helped |
| Use TEA rather than rank-1 Elimination | Rank-1 bandits · Rank-1 bandits | regret | Helped |
Closest papers by meaning
- Factored-Reward Bandits with Intermediate Observations (ICML 2024 · similarity 0.91)
- Fusing Reward and Dueling Feedback in Stochastic Bandits (ICML 2025 · similarity 0.91)
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits (ICLR 2024 · similarity 0.90)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (NeurIPS 2025 · similarity 0.89)
- On Weak Regret Analysis for Dueling Bandits (NeurIPS 2024 · similarity 0.89)
- Bandits with Ranking Feedback (NeurIPS 2024 · 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.