EconBase
← All papers

Minimax Optimal Kernel Operator Learning via Multilevel Training

Jikai Jin, Yiping Lu, Jose Blanchet, Lexing Ying

arXiv 28 Sep 2022 · Machine Learning · 1 citations (OpenAlex)

arXiv:2209.14430 · PDF · DOI · OpenAlex · Extracted main text

Abstract

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.

Citation extraction

73
references
166
in-text mentions
73
distinct cited
11
self-citations
7,763
main-text words

appendix boundary found by appendix_command · 40% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Li, Zhu, Meunier, Dimitri, Mollenhauer, Mattes, Gretton, Arthur (2022) Optimal Rates for Regularized Conditional Mean Embedding Learning1.000144100%
2Hoop, Maarten V, Kovachki, Nikola B, Nelsen, Nicholas H, Stuart, And… (2021) Convergence rates for learning linear operators from noisy data1.000113100%
3Lu, Yiping, Blanchet, Jose, Ying, Lexing (2022) Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent self1.00054100%
4Talwai, Prem, Shameli, Ali, Simchi-Levi, David (2022) Sobolev Norm Learning Rates for Conditional Mean Embeddings0.97614593%
5Lu, Lu, Jin, Pengzhan, Karniadakis, George Em (2019) Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of op…0.92843100%
6Fischer, Simon, Steinwart, Ingo (2020) Sobolev Norm Learning Rates for Regularized Least-Squares Algorithms.0.88022768%
7Li, Zhihan, Fan, Yuwei, Ying, Lexing (2021) Multilevel fine-tuning: Closing generalization gaps in approximation of solution maps under a limited budget for training data self0.87452100%
8Lye, Kjetil O, Mishra, Siddhartha, Molinaro, Roberto (2021) A multi-level procedure for enhancing accuracy of machine learning algorithms0.87452100%
9Boullé, Nicolas, Kim, Seick, Shi, Tianyi, Townsend, Alex (2022) Learning Green’s functions associated with time-dependent partial differential equations0.81142100%
10Giles, Michael B (2008) Multilevel monte carlo path simulation0.73732100%

Showing the top 10 of 73 scored citations.