Learning functions, operators and dynamical systems with kernels
By: Lorenzo Rosasco
Potential Business Impact:
Teaches computers to learn from data.
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.
Similar Papers
Learning Spatio-Temporal Dynamics via Operator-Valued RKHS and Kernel Koopman Methods
Machine Learning (CS)
Predicts how things change over time and space.
A Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learning
Machine Learning (Stat)
Teaches computers to solve hard math problems.
Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learning
Machine Learning (Stat)
Teaches computers to solve hard math problems.