paper-with-me

Papers

Learning functions, operators and dynamical systems with kernels

2025-09-22 · Lorenzo Rosasco arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.18071

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SFO: Learning PDE Operators via Spectral Filtering

2026-01-23 · Noam Koren, Rafael Moschopoulos, Kira Radinsky, Elad Hazan arxiv

Partial differential equations (PDEs) govern complex systems, yet neural operators often struggle to efficiently capture the long-range, nonlocal interactions inherent in their solution maps. We introduce Spectral Filter…

On Dynamic Mode Decomposition of Control-affine Systems

2025-03-13 · Moad Abudia, Joel A. Rosenfeld, Rushikesh Kamalapurkar

This paper builds on the theoretical foundations for dynamic mode decomposition (DMD) of control-affine dynamical systems by leveraging the theory of vector-valued reproducing kernel Hilbert spaces (RKHSs). Specifically,…

Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spaces

2024-03-04 · Isao Ishikawa, Yuka Hashimoto, Masahiro Ikeda, Yoshinobu Kawahara

This paper presents a novel approach for estimating the Koopman operator defined on a reproducing kernel Hilbert space (RKHS) and its spectra. We propose an estimation method, what we call Jet Dynamic Mode Decomposition …

Dissipative Deep Neural Dynamical Systems

2020-11-26 · Jan Drgona, Soumya Vasisht, Aaron Tuor, Draguna Vrabie

In this paper, we provide sufficient conditions for dissipativity and local asymptotic stability of discrete-time dynamical systems parametrized by deep neural networks. We leverage the representation of neural networks …

Kernel Methods for Stochastic Dynamical Systems with Application to Koopman Eigenfunctions: Feynman-Kac Representations and RKHS Approximation

2026-03-01 · Boumediene Hamzi, Houman Owhadi, Umesh Vaidya arxiv

We extend the unified kernel framework for transport equations and Koopman eigenfunctions, developed in previous work by the authors for deterministic systems, to stochastic differential equations (SDEs). In the determin…