OpenAlex ·
Optimality of Affine Policies in Distributionally Robust Linear-Quadratic Control with Temporally Correlated Noise
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2609.27653
- Original
- Read it at the publisher
- Topics
Abstract
We study finite-horizon distributionally robust linear-quadratic control with disturbances that can be arbitrarily correlated in time. The ambiguity set is modeled as a single 2-Wasserstein ball centered at a nominal elliptically contoured distribution of the disturbances. Despite the infinite-dimensionality of both the policy space and ambiguity set, we prove that the optimal policy is affine and that the worst-case distribution is an affine push-forward of the nominal distribution. These affine maps can be computed efficiently via a best-response algorithm based on the Frank--Wolfe algorithm. Experiments demonstrate improved out-of-sample performance over LQG and its distributionally robust extensions when the true disturbances are correlated, incurring only a small loss of performance under uncorrelated disturbances.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Systems & Control
ZO-COSMO: Index-Free One-Hop Mixing for Decentralized Zeroth-Order Optimization
Precise Convergence Speed of Clipped SGD
Distributed Stochastic Approximation Algorithms and Heavy-Tailed Age of Information
Shrinking-Tube Concentration for Adaptive Markovian Stochastic Approximation
Limiting-Kernel Q($λ$): Bridging Short and Long Horizons
Get the few papers worth your time in Systems & Control every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.