Research map / Bandits and online learning / Multi-armed bandits
Statistical Inference on Multi-armed Bandits with 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 Hajek (self-normalized) weighting instead of plain IPW normalization by T (ablation) | delay-adjusted estimator under vanishing propensity scores · epsilon-greedy simulation, no finite delay | absolute bias and CI validity | Helped |
| Adaptive weights h_t(a)=sqrt(pi_t(a)) (constant allocation) with delay adjustment (ablation) | DAIPW estimator · epsilon-greedy simulation with margins | normal approximation quality | Helped |
| Remove adaptive weighting (use sample mean with delay adjustment) (ablation) | Mean estimator · epsilon-greedy simulation, no finite delay | absolute bias and CI length | Hurt |
| Remove outcome model adjustment and delay adjustment (NH0 plain IPW) (ablation) | IPW estimator · epsilon-greedy with margins | bias | Hurt |
| Use non-Hajek AIPW (NH) instead of Hajek-type normalization (ablation) | AIPW estimator · epsilon-greedy zero margin | approximation to normal / accuracy | Hurt |
Closest papers by meaning
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · similarity 0.90)
- Delay as Payoff in MAB (AAAI 2025 · similarity 0.89)
- Simulation-Based Inference for Adaptive Experiments (NeurIPS 2025 · similarity 0.89)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.88)
- Contextual Linear Bandits with Delay as Payoff (ICML 2025 · similarity 0.88)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.88)
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.