Research map / Bandits and online learning / Multi-armed bandits
A unified framework for bandit multiple testing
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 e-processes with e-BH instead of p-processes with BH | Bandit multiple testing · Arbitrary dependence, exploration strategies, and stopping times | FDR control: e-BH at level \delta guarantees FDR ≤ \delta; BH may require a \log k correction | Helped |
| Use discrete mixture e-processes with UCB exploration | Bandit multiple testing with independent 1-sub-Gaussian arms · Independent 1-sub-Gaussian arms | sample complexity for high TPR: T \lesssim \left(\sum_{i = 1}^k \gap_i^{-2}\log\log \gap_i^{-2} + \gap_i^{-2}\log(k / \delta)\right) \wedge k\gap^{-2}\l | No clear effect |
| Replace p-variables and BH with e-variables and e-BH while keeping uniform sampling | Bandit multiple testing simulations · Gaussian arms; uniform sampling | time to reach target TPR and FDR | Helped |
| Replace p-variables and BH with e-variables and e-BH while keeping UCB sampling | Bandit multiple testing simulations · Gaussian arms; UCB sampling | time to reach target TPR and FDR | No clear effect |
Closest papers by meaning
- Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams (ICML 2024 · similarity 0.88)
- Testing the Feasibility of Linear Programs with Bandit Feedback (ICML 2024 · similarity 0.88)
- The Batch Complexity of Bandit Pure Exploration (ICML 2025 · similarity 0.88)
- Infrequent Exploration in Linear Bandits (NeurIPS 2025 · similarity 0.88)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (NeurIPS 2025 · similarity 0.87)
- Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach (AAAI 2024 · similarity 0.87)
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.