A New Approach to Controlling Linear Dynamical Systems
Not on the map. Why?
Abstract (arXiv)
We propose a new method for controlling linear dynamical systems under adversarial disturbances and cost functions. Our algorithm achieves a running time that scales polylogarithmically with the inverse of the stability margin, improving upon prior methods with polynomial dependence maintaining the same regret guarantees. The technique, which may be of independent interest, is based on a novel convex relaxation that approximates linear control policies using spectral filters constructed from the eigenvectors of a specific Hankel matrix.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 4 Apr 2025.
Builds on
21 of 37 references.
References · 21
- 2019Introduction to Online Convex Optimizationcited by 803
- 2019Online Control with Adversarial Disturbancescited by 92
- 2018Near optimal finite time identification of arbitrary linear dynamical systemscited by 89
- 2018Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulatorcited by 86
- 2020Improper Learning for Non-Stochastic Controlcited by 83
- 2016Gradient Descent Learns Linear Dynamical Systemscited by 79
- 2019Learning Linear-Quadratic Regulators Efficiently with only √T Regretcited by 70
- 2018Online Linear Quadratic Controlcited by 56
- 2017Learning Linear Dynamical Systems via Spectral Filteringcited by 46
- 2020Logarithmic Regret for Adversarial Online Controlcited by 41
- 2019Logarithmic Regret for Online Controlcited by 38
- 2018Spectral Filtering for General Linear Dynamical Systemscited by 37
9 more
- 2023A New Approach to Learning Linear Dynamical Systemscited by 23
- 2022Introduction to Online Controlcited by 19
- 2022Learning Mixtures of Linear Dynamical Systemscited by 15
- 2022Online Control of Unknown Time-Varying Dynamical Systemscited by 13
- 2023Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systemscited by 10
- 2023Optimal Rates for Bandit Nonstochastic Controlcited by 7
- 2024FutureFill: Fast Generation from Convolutional Sequence Modelscited by 7
- 2025Universal Sequence Preconditioningcited by 6
- 2025Population Dynamics Control with Partial Observationscited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.