Koopman operator learning for predictive control via Khatri-Rao kernel regression

arXiv:2606.02938 · math.OC, cs.SY, eess.SY · Submitted 2026-06-01 · Read on arXiv

math.OC, cs.SY, eess.SY

Submitted: 2026-06-01

Updated: 2026-10-15

Comments: Revised paper: updated the simulation section with comparison against linear Koopman models and clarified several implementation aspects

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

Terminology

• Koopman Operator — 2× in this paper · explained in 4 episodes

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning
• Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets
• Second-Order Optimization with Asynchronous Curvature