English

Online Infinite-Dimensional Regression: Learning Linear Operators

Machine Learning 2024-01-26 v3 Machine Learning

Abstract

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 pp-Schatten norm is online learnable for any p[1,)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.

Keywords

Cite

@article{arxiv.2309.06548,
  title  = {Online Infinite-Dimensional Regression: Learning Linear Operators},
  author = {Vinod Raman and Unique Subedi and Ambuj Tewari},
  journal= {arXiv preprint arXiv:2309.06548},
  year   = {2024}
}

Comments

21 pages, ALT 2024 Camera Ready

R2 v1 2026-06-28T12:19:43.502Z