Score: 0

Learning functions, operators and dynamical systems with kernels

Published: September 22, 2025 | arXiv ID: 2509.18071v2

By: Lorenzo Rosasco

Potential Business Impact:

Teaches computers to learn from data.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

This expository article presents the approach to statistical machine learning based on reproducing kernel Hilbert spaces. The basic framework is introduced for scalar-valued learning and then extended to operator learning. Finally, learning dynamical systems is formulated as a suitable operator learning problem, leveraging Koopman operator theory. The manuscript collects the supporting material for the corresponding course taught at the CIME school "Machine Learning: From Data to Mathematical Understanding" in Cetraro.

Page Count
24 pages

Category
Computer Science:
Machine Learning (CS)