Online Infinite-Dimensional Regression: Learning Linear Operators
Preprint
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 $p$-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 online 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 agnostic PAC setting.
Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Model Reduction And Neural Networks For Parametric PDEsThe SMAI journal of computational mathematics, 2021
- Operator learning for predicting multiscale bubble growth dynamicsThe Journal of Chemical Physics, 2021
- Data-driven approximation of the Koopman generator: Model reduction, system identification, and controlPhysica D: Nonlinear Phenomena, 2020
- Inverse Problem Theory and Methods for Model Parameter Estimation2005
- On the Generalization Ability of On-Line Learning AlgorithmsIEEE Transactions on Information Theory, 2004
- Competitive On-Line StatisticsInternational Statistical Review, 2001