Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Online Stochastic Linear Optimization under One-bit 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 lazy updating (recompute x_t only when det(Z_t) grows by factor (1+c)) | OL2M · theoretical regret bound | regret and computation: regret only increased by a constant factor sqrt(1+c) | Mixed |
| lazy updating reduces optimization solves | OL2M · computation cost | number of optimization solves | Helped |
| replace nonlinear logit regret by the linear regret | OL2M analysis · regret definition | regret | No clear effect |
| use online Newton step with exponential concavity of logistic loss instead of generalized linear bandit estimator | OL2M · stochastic linear optimization with one-bit feedback | regret bound | Helped |
| restrict action set D to the unit ball | OL2M · action selection | computation time | Helped |
Closest papers by meaning
- Delay and Cooperation in Nonstochastic Linear Bandits (NeurIPS 2020 · similarity 0.90)
- Bandit Online Linear Optimization with Hints and Queries (ICML 2023 · similarity 0.90)
- Linear bandits with Stochastic Delayed Feedback (ICML 2020 · similarity 0.89)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.89)
- Batched Stochastic Linear Bandits with 1-Bit Communication Constraints (NeurIPS 2026 · similarity 0.89)
- Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting (AAAI 2025 · 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.