Research map / Bandits and online learning / Online convex optimization and games
Online Control with Adversarial Disturbances
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 online disturbance-action policies optimized with OGD and memory | Linear dynamical systems with bounded adversarial disturbances · Adversarial LDS with convex costs | regret: O(\sqrt{T}) | Helped |
| Allow adversarially chosen convex costs instead of restricting costs to quadratic functions | Online control algorithm · Adversarial LDS | regret: O\left(G W^2 \sqrt{T} \log(T)\right) | Helped |
| Adapt the controller online to observed disturbances rather than choosing control for worst-case future noise | Online Control Algorithm · Linear dynamical systems with adversarial disturbances | regret: O(\sqrt{T}) | Helped |
Closest papers by meaning
- Logarithmic Regret for Adversarial Online Control (ICML 2020 · similarity 0.91)
- Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances (NeurIPS 2026 · similarity 0.90)
- Rate-Optimal Online Convex Optimization in Adaptive Linear Control (NeurIPS 2022 · similarity 0.90)
- Making Non-Stochastic Control (Almost) as Easy as Stochastic (NeurIPS 2020 · similarity 0.90)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.89)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.86)
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.