paper-with-me

Papers

Online Infinite-Dimensional Regression: Learning Linear Operators

2023-09-08 · Vinod Raman, Unique Subedi, Ambuj Tewari

We consider the problem of learning linear operators under squared loss between two infinite-dimensional Hilbert spaces in the online setting. We show that the class of linear operators with uniformly bounded $p$-Schatten norm is online learnable for any $p \in [1, \infty)$. On the other hand, we prove an impossibility result by showing that the class of uniformly bounded linear operators with respect to the operator norm is \textit{not} online learnable. Moreover, we show a separation between sequential uniform convergence and online learnability by identifying a class of bounded linear operators that is online learnable but uniform convergence does not hold. Finally, we prove that the impossibility result and the separation between uniform convergence and learnability also hold in the batch setting.

📄 PDF Abstract BibTeX arXiv:2309.06548

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Universal Approximation of Nonlinear Operators and Their Derivatives

2026-05-14 · Filippo de Feo arxiv

Establishing Universal Approximation Theorems (UATs) for nonlinear operators and their derivatives is a foundational open problem in Operator Learning (OL) and raises delicate questions in Nonlinear Functional Analysis. …

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

2022-11-16 · Mattes Mollenhauer, Nicole Mücke, T. J. Sullivan

We consider the problem of learning a linear operator $\theta$ between two Hilbert spaces from empirical observations, which we interpret as least squares regression in infinite dimensions. We show that this goal can be …

regression

Rigorous data-driven computation of spectral properties of Koopman operators for dynamical systems

2021-11-29 · Matthew J. Colbrook, Alex Townsend

Koopman operators are infinite-dimensional operators that globally linearize nonlinear dynamical systems, making their spectral information valuable for understanding dynamics. However, Koopman operators can have continu…

Learning Schatten--von Neumann Operators

2019-01-29 · Puoya Tabaghi, Maarten de Hoop, Ivan Dokmanić

We study the learnability of a class of compact operators known as Schatten--von Neumann operators. These operators between infinite-dimensional function spaces play a central role in a variety of applications in learnin…

Learning Theory

Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems

2022-10-06 · Lianghao Cao, Thomas O'Leary-Roseberry, Prashant K. Jha, J. Tinsley Oden 외

We explore using neural operators, or neural network representations of nonlinear maps between function spaces, to accelerate infinite-dimensional Bayesian inverse problems (BIPs) with models governed by nonlinear parame…