Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem

11/16/2022
by   Mattes Mollenhauer, et al.
0

We consider the problem of learning a linear operator θ between two Hilbert spaces from empirical observations, which we interpret as least squares regression in infinite dimensions. We show that this goal can be reformulated as an inverse problem for θ with the undesirable feature that its forward operator is generally non-compact (even if θ is assumed to be compact or of p-Schatten class). However, we prove that, in terms of spectral properties and regularisation theory, this inverse problem is equivalent to the known compact inverse problem associated with scalar response regression. Our framework allows for the elegant derivation of dimension-free rates for generic learning algorithms under Hölder-type source conditions. The proofs rely on the combination of techniques from kernel regression with recent results on concentration of measure for sub-exponential Hilbertian random variables. The obtained rates hold for a variety of practically-relevant scenarios in functional regression as well as nonlinear regression with operator-valued kernels and match those of classical kernel regression with scalar response.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2012

Multiple Operator-valued Kernel Learning

Positive definite operator-valued kernels generalize the well-known noti...
research
10/10/2019

On the Dualization of Operator-Valued Kernel Machines

Operator-Valued Kernels (OVKs) and Vector-Valued Reproducing Kernel Hilb...
research
01/29/2019

Learning Schatten--Von Neumann Operators

We study the learnability of a class of compact operators known as Schat...
research
06/23/2022

Sliced Inverse Regression in Metric Spaces

In this article, we propose a general nonlinear sufficient dimension red...
research
06/11/2021

Learning the optimal regularizer for inverse problems

In this work, we consider the linear inverse problem y=Ax+ϵ, where A X→ ...
research
06/08/2022

Open questions asked to analysis and numerics concerning the Hausdorff moment problem

We address facts and open questions concerning the degree of ill-posedne...
research
06/05/2022

The Lindeberg-Feller and Lyapunov Conditions in Infinite Dimensions

The Lindeberg-Feller and Lyapunov Central Limit Theorems are generalized...

Please sign up or login with your details

Forgot password? Click here to reset