Research map / Bandits and online learning / Online convex optimization and games
Bandit Online Linear Optimization with Hints and Queries
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 |
|---|---|---|---|
| Add good hints (⟨h_t,c_t⟩ ≥ 1/4 at every step) to bandit OLO | Bandit OLO in two dimensions with unit ball domain · Lower bound construction (Theorem 3.1) | expected regret | No clear effect |
| Add query access (algorithm queries inner product with a uniformly random unit-sphere point) and use the response to build cost estimate and hint | Bandit OLO with queries (Algorithm 1) · all query responses good (B=0) | expected regret | Helped |
| Increase number of bad query responses B under Algorithm 1 | Bandit OLO with queries (Algorithm 1) · regret bound with B bad responses | expected regret | Hurt |
| Add binary response feedback (gt) after playing, with hint weight learner and Dikin-ellipsoid exploration | Bandit OLO with queries and response feedback (Algorithm 2) · regret bound with B bad responses | expected regret | Helped |
Closest papers by meaning
- Online Linear Optimization with Many Hints (NeurIPS 2020 · similarity 0.92)
- Online Learning with Imperfect Hints (ICML 2020 · similarity 0.92)
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (NeurIPS 2024 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Testing the Feasibility of Linear Programs with Bandit Feedback (ICML 2024 · similarity 0.88)
- Tight Rates for Bandit Control Beyond Quadratics (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.