Research map / Bandits and online learning / Multi-armed bandits
Bandits with Delayed, Aggregated Anonymous 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 phase-based elimination with knowledge of expected delay | ODA AAF · MABDAAF with known expected delay | expected regret: O(\sqrt{KT\log K} + K\mathbb{E}[\tau]\log T) | Helped |
| Add known bounded-delay information and bridge periods | ODA AAF · MABDAAF with bounded delay | expected regret: O(\sqrt{KT\log(K)} + K\mathbb{E}[\tau]) | Helped |
| Add known delay-variance information | ODA AAF · MABDAAF with unbounded delays and known variance | expected regret: O(\sqrt{KT\log(K)} + K\mathbb{E}[\tau] + K \mathbb{V}(\tau)) | Mixed |
| Use delay-variance information when variance is small (ablation) | ODA AAF-V · Unbounded delays with small variance | regret | Helped |
| Use delay-variance information with exponential delays (ablation) | ODA AAF-V · Exponential delays | regret | Hurt |
| Use ODA AAF or its bounded-delay/variance variants instead of relying on non-anonymous feedback | ODA AAF versus QPM-D · Tested delay distributions | regret | No clear effect |
| Increase expected delay | ODA AAF and QPM-D · Experimental delay settings | regret | Hurt |
Closest papers by meaning
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · similarity 0.92)
- 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)
- Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting (AAAI 2025 · similarity 0.88)
- Fusing Reward and Dueling Feedback in Stochastic Bandits (ICML 2025 · similarity 0.88)
- Bandits with Ranking Feedback (NeurIPS 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.