Research map / Bandits and online learning / Contextual bandits and Thompson sampling
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
Weitong Zhang, Jiafan He, Zhiyuan Fan, Quanquan Gu
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 data selection with threshold Γ=0.05 instead of using all data (Γ=0) (ablation) | OFUL / DS-OFUL · Synthetic dataset | cumulative regret (mean ± std.): 405.4\pm76.5 -> 235.75 \pm 40.3 | Improved |
| Increase the data-selection threshold to Γ=0.13 (ablation) | DS-OFUL · Synthetic dataset | cumulative regret (mean ± std.): 235.75 \pm 40.3 -> 1789.5\pm1918.8 | Hurt |
| Use Γ=0.05 rather than Γ=0.08 (ablation) | DS-OFUL · Synthetic dataset | cumulative regret (mean ± std.): 411.6\pm566.7 -> 235.75 \pm 40.3 | Mixed |
| Use Γ=0.05 rather than Γ=0.02 (ablation) | DS-OFUL · Synthetic dataset | cumulative regret (mean ± std.): 326.5\pm68.0 -> 235.75 \pm 40.3 | Improved |
Closest papers by meaning
- Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification (NeurIPS 2024 · similarity 0.90)
- Second Order Bounds for Contextual Bandits with Function Approximation (ICLR 2025 · similarity 0.89)
- Mixed-Effects Contextual Bandits (AAAI 2024 · similarity 0.89)
- Generalized Linear Bandits with Limited Adaptivity (NeurIPS 2024 · similarity 0.89)
- Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error (ICLR 2025 · similarity 0.89)
- How Does Variance Shape the Regret in Contextual Bandits? (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.
