Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Universal and data-adaptive algorithms for model selection 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 |
|---|---|---|---|
| Replace the ordinary inverse-covariance estimator with eigenvalue thresholding | ModCB · MAB-vs-linear CB with arbitrary stochastic sub-Gaussian contexts | model-selection rate exponent alpha: 1/3 -> 1/6 | Helped |
| Use data-adaptive exploration that checks whether the greedy arm's context preserves diversity | ModCB.A · MAB-vs-linear CB when every arm has feature diversity | simple-model regret: T^{2/3} -> \log(T)/\textrm{gap} | Helped |
| Use data-adaptive exploration while retaining forced exploration when the diversity check fails | ModCB.A · MAB-vs-linear CB under arm-averaged feature diversity | contextual-model regret: d^{1/3}T^{2/3} -> d^{1/3}T^{2/3} | No clear effect |
| Require arm-specific rather than only arm-averaged feature diversity | OSOM · MAB-vs-linear CB | model-selection guarantee | Hurt |
Closest papers by meaning
- Model Selection for Contextual Bandits (NeurIPS 2019 · similarity 0.96)
- Model Selection in Contextual Stochastic Bandit Problems (NeurIPS 2020 · similarity 0.93)
- Feature and Parameter Selection in Stochastic Linear Bandits (ICML 2022 · similarity 0.92)
- An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits (NeurIPS 2020 · similarity 0.91)
- Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates (ICML 2026 · similarity 0.91)
- Generalized Linear Bandits with Limited Adaptivity (NeurIPS 2024 · similarity 0.91)
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.