Learning linear dynamical systems under convex constraints

arXiv:2303.15121 · math.ST, cs.SY, eess.SY, math.OC, stat.ML, stat.TH · Submitted 2023-03-27 · Read on arXiv

math.ST, cs.SY, eess.SY, math.OC, stat.ML, stat.TH

Submitted: 2023-03-27

Updated: 2026-10-11

Comments: 31 pages; corrected typos and added additional explanations at certain places; minor corrections in proofs of Corollary 4 and Theorem 2

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• Subgradient Regularized Multivariate Convex Regression at Scale
• Joint learning of a network of linear dynamical systems via total variation penalization
• Convex Regression in Multidimensions: Suboptimality of Least Squares Estimators
• Large Vector Auto Regressions
• Various thresholds for $\ell_1$-optimization in compressed sensing

Related papers

• Conformal Prediction for Dyadic Regression Under Complex Missingness
• Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel
• Bentkus-type asymptotic e-values
• High-Dimensional Asymptotics of Differentially Private PCA
• A proximal gradient algorithm for composite log-concave sampling
• KL Convergence Guarantees for Score diffusion models under minimal data assumptions