Research map / Bandits and online learning / Contextual bandits and Thompson sampling
The Pareto Frontier of model selection for general Contextual Bandits
Teodor Vanislavov Marinov, Julian Zimmert
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 Hedged-FTRL to combine EXP4 instances across policy classes | Contextual bandits with nested finite policy classes · General CB, adaptive adversary | regret: \cO(\max\{\mathfrak{C},\frac{\ln|\Pi_m|}{\mathfrak{C}}\}\sqrt{MKT}) | Improved |
| Require simultaneous guarantees across policy classes | Contextual bandits with nested finite policy classes · Stochastic environments, proper or improper algorithms | regret | Hurt |
| Seek a second-order full-information bound simultaneously for every fraction of experts | Full-information experts · Variance-adaptive regret | regret | Hurt |
Closest papers by meaning
- Model Selection for Contextual Bandits (NeurIPS 2019 · similarity 0.91)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.87)
- Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning (NeurIPS 2024 · similarity 0.87)
- Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk (NeurIPS 2026 · similarity 0.86)
- Generalized Linear Bandits with Limited Adaptivity (NeurIPS 2024 · similarity 0.86)
- Nearly Minimax Optimal Regret for Multinomial Logistic Bandit (NeurIPS 2024 · similarity 0.86)
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.
