Research map / Bandits and online learning / Contextual bandits and Thompson sampling
High-Dimensional Sparse 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 informative-design exploration followed by Lasso estimation and greedy commitment | ESTC for sparse linear bandits · Data-poor sparse linear bandits | cumulative regret: \cO(C_{\min}^{-2/3}s^{2/3}n^{2/3}) upper bound; the paper states this matches the \Omega(n^{2/3}) rate in horizon depend | Helped |
| Require a minimum signal and screen features with Lasso before restricted phase elimination | Sparse linear bandits · Sparse linear bandits with minimum signal | cumulative regret: \cO(\sqrt{sn}) regret when C_{\min}(\cA) is dimension-free and m\geq (s\log^2(d)/C_{\min}(\cA)n)^{1/4} | Helped |
| Use ESTC in place of LinUCB | Linear contextual bandits and the hard problem instance · Experiments, Cases 1 and 2 | regret | Helped |
| Use ESTC in place of DR-Lasso | Linear contextual bandits and the hard problem instance · Experiments, Cases 1 and 2 | regret | Mixed |
Closest papers by meaning
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (NeurIPS 2024 · similarity 0.92)
- High-dimensional Linear Bandits with Knapsacks (ICML 2024 · similarity 0.91)
- Regret minimization in Linear Bandits with offline data via extended D-optimal exploration. (NeurIPS 2026 · similarity 0.90)
- Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits (ICLR 2025 · similarity 0.90)
- Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards (NeurIPS 2025 · similarity 0.90)
- Lasso Bandit with Compatibility Condition on Optimal Arm (ICLR 2025 · 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.