Research map / Bandits and online learning / Online convex optimization and games
Bandit Linear Control
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 strongly convex and smooth costs | Bandit Linear Control · Bandit linear control | pseudo-regret growth rate: \tilde{O}(\sqrt{T}) | Helped |
| Allow weakly convex costs without requiring smoothness | Bandit Linear Control · Bandit linear control with oblivious adversarial system noise | regret growth rate: \tilde{O}(T^{3/4}) | Mixed |
| Require smooth costs in the weakly convex setting | Bandit Linear Control · Bandit linear control with oblivious adversarial system noise | regret growth rate: \tilde{O}(T^{3/4}) -> \tilde{O}(T^{2/3}) | Helped |
| Use the new reduction for bandit optimization with bounded memory rather than mini-batching | Bandit convex optimization with memory · Smooth bounded-memory losses | regret growth rate: O(T^{2/3}) -> O(T^{1/2}) | Helped |
Closest papers by meaning
- Non-Stochastic Control with Bandit Feedback (NeurIPS 2020 · similarity 0.96)
- Tight Rates for Bandit Control Beyond Quadratics (NeurIPS 2024 · similarity 0.93)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS 2024 · similarity 0.90)
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · similarity 0.90)
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (NeurIPS 2024 · similarity 0.89)
- Batched Stochastic Linear Bandits with 1-Bit Communication Constraints (NeurIPS 2026 · similarity 0.89)
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.