Research map / Bandits and online learning / Multi-armed bandits
Thresholding Bandit with Optimal Aggregate Regret
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 LSA instead of Uniform, APT, UCBE, or Opt-KG | Thresholding bandit · Setup 1 (arithmetic progression I) | aggregate regret | Helped |
| Use LSA instead of the competing algorithms | Thresholding bandit · Setup 2 (arithmetic progression II) | aggregate regret | Helped |
| Use LSA instead of the competing algorithms | Thresholding bandit · Setup 3 (two-group setting) | aggregate regret | Helped |
| Use a fixed LSA tuning parameter across setups rather than selecting APT's precision parameter for each setting and budget | LSA and APT · Thresholding bandit, Setups 1–3 | robustness across settings | Helped |
| Use uniform sampling instead of optimal budget allocation | Thresholding bandit · Constructed hard instances, K ≥ 20 | budget required for the same order of aggregate regret: Ω(K) | Hurt |
Closest papers by meaning
- An optimal algorithm for the Thresholding Bandit Problem (ICML 2016 · similarity 0.92)
- On Regret with Multiple Best Arms (NeurIPS 2020 · similarity 0.92)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Nearly Minimax Optimal Submodular Maximization with Bandit Feedback (NeurIPS 2024 · similarity 0.89)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 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.