Learning functions, operators and dynamical systems with kernels

Seminario periodico del Dipartimento di Matematica
10 November 2023
Start time 
2:03 pm
Polo Ferrari 1 - Via Sommarive 5, Povo (Trento)
Room A204 – Povo1 e online via Zoom (contattare per le credenziali)
Target audience: 
University community
UniTrento students
Registration email: 
Contact person: 
Prof. Gian Paolo Leonardi
Contact details: 
Università degli Studi Trento 38123 Povo (TN) - Staff Dipartimento di Matematica
+39 0461/281508-1625-1701-1980-3898-1511
Lorenzo Rosasco (Università di Genova)


Supervised machine learning is concerned with the problem of estimating a function of interest from a random set of input/output pairs. While classically real-valued functions are considered,
there is a growing interest in estimating more complex maps such as linear and nonlinear operators.
In this talk, I will describe how these questions can be tackled using kernel methods. I will show how classical results for scalar-valued functions seamlessly extend to operators.
Then, I will describe how this approach can be used to learn dynamical systems by estimating the corresponding Koopman operator.