Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Breaking the $\sqrtT$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear 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 LR-SCB's epoch-wise parameter estimation, reward shifting, and norm-adaptive learning instead of OFUL | Stochastic contextual linear bandits · Stochastic contextual linear bandits | regret: \mathcal{O}(\sqrt{T}) -> \mathcal{O}(\mathsf{polylog}(T)) | Helped |
| Use LR-SCB rather than OFUL | Uniform stochastic contexts with K = 20 and d = {20,15,30} · Uniform stochastic contexts; K = 20 and d = {20,15,30} | regret | Helped |
| Shift the parameter by a fixed vector in shifted OFUL | OFUL · Stochastic contextual linear bandits | regret | Hurt |
| Increase epoch lengths as T_i = T_1 (\log T)^{i-1} | LR-SCB · Stochastic contextual linear bandits | regret | Helped |
Closest papers by meaning
- Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit (NeurIPS 2024 · similarity 0.93)
- Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions (NeurIPS 2026 · similarity 0.92)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.91)
- How Does Variance Shape the Regret in Contextual Bandits? (NeurIPS 2024 · similarity 0.90)
- Mixed-Effects Contextual Bandits (AAAI 2024 · similarity 0.90)
- Generalized Linear Bandits with Limited Adaptivity (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.