Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Linear bandits with Stochastic Delayed Feedback
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 OTFLinUCB instead of OTFLinTS | the proposed delayed linear bandit algorithms · Geometric delays, all three reported (m, μ) settings | cumulative regret | Helped |
| Increase the window from m=100 to m=500 (ablation) | OTFLinUCB · Geometric delays with μ=100 | cumulative regret | Mixed |
| Set the window below the mean delay, with m=100 and μ=500 (ablation) | OTFLinUCB and OTFLinTS · Geometric delays | cumulative regret: 1/τ_m = 5.5 | Hurt |
| Use a window larger than the mean delay, with m=500 and μ=100 (ablation) | OTFLinUCB and OTFLinTS · Geometric delays | cumulative regret: τ_m=0.993 | Helped |
| Use a window m=2000 with delays drawn from an empirical heavy-tailed distribution (ablation) | OTFLinUCB · Heavy-tailed delays | cumulative regret | No clear effect |
Closest papers by meaning
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · similarity 0.93)
- Delay and Cooperation in Nonstochastic Linear Bandits (NeurIPS 2020 · similarity 0.91)
- Learning in Generalized Linear Contextual Bandits with Stochastic Delays (NeurIPS 2019 · similarity 0.91)
- Contextual Linear Bandits with Delay as Payoff (ICML 2025 · similarity 0.90)
- Delay as Payoff in MAB (AAAI 2025 · similarity 0.89)
- A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays (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.