paper-with-me

Papers

Minimax Optimal Kernel Operator Learning via Multilevel Training

2022-09-28 · Jikai Jin, Yiping Lu, Jose Blanchet, Lexing Ying

Learning mappings between infinite-dimensional function spaces has 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 that are 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.

📄 PDF Abstract BibTeX arXiv:2209.14430

Code (0)

등록된 구현이 없습니다.

Tasks

Causal InferenceMulti-agent Reinforcement LearningOperator learning

Similar Papers 제목 키워드 기반

Minimax Estimation of Kernel Stein Discrepancy: Trace versus Hilbert-Schmidt Scales

2026-07-03 · Davit Gogolashvili arxiv

Kernel Stein Discrepancy (KSD) compares a sample to a fixed target distribution known only through its score, and is widely used for goodness-of-fit testing, sample quality assessment, and approximate inference. We study…

Minimax Optimal Kernel Two-Sample Tests with Random Features

2025-02-28 · Soumya Mukherjee, Bharath K. Sriperumbudur

Reproducing Kernel Hilbert Space (RKHS) embedding of probability distributions has proved to be an effective approach, via MMD (maximum mean discrepancy) for nonparametric hypothesis testing problems involving distributi…

Computational Efficiency

Optimal Convergence Rates for Neural Operators

2024-12-23 · Mike Nguyen, Nicole Mücke

We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive fast convergence rates that are known to …

Random Features for Operator-Valued Kernels: Bridging Kernel Methods and Neural Operators

2026-03-01 · Mike Nguyen, Nicole Mücke arxiv

In this work, we investigate the generalization properties of random feature methods. Our analysis extends prior results for Tikhonov regularization to a broad class of spectral regularization techniques and further gene…

The Minimax Lower Bound of Kernel Stein Discrepancy Estimation

2025-10-16 · Jose Cribeiro-Ramallo, Agnideep Aich, Florian Kalinke, Ashit Baran Aich 외 arxiv

Kernel Stein discrepancies (KSDs) have emerged as a powerful tool for quantifying goodness-of-fit over the last decade, featuring numerous successful applications. To the best of our knowledge, all existing KSD estimator…