Skip to yearly menu bar Skip to main content


In-Person Poster presentation / top 25% paper

Minimax Optimal Kernel Operator Learning via Multilevel Training

Jikai Jin · Yiping Lu · Jose Blanchet · Lexing Ying

MH1-2-3-4 #72

Keywords: [ Machine Learning for Sciences ]


Abstract:

Learning mappings between infinite-dimensional function spaces have achieved empirical success in many disciplines of machine learning, including generative modeling, functional data analysis, causal inference, and multi-agent reinforcement learning. In this paper, we study the statistical limit of learning a Hilbert-Schmidt operator between two infinite-dimensional Sobolev reproducing kernel Hilbert spaces. We establish the information-theoretic lower bound in terms of the Sobolev Hilbert-Schmidt norm and show that a regularization that learns the spectral components below the bias contour and ignores the ones above the variance contour can achieve the optimal learning rate. At the same time, the spectral components between the bias and variance contours give us flexibility in designing computationally feasible machine learning algorithms. Based on this observation, we develop a multilevel kernel operator learning algorithm that is optimal when learning linear operators between infinite-dimensional function spaces.

Chat is not available.