Two-layer neural network on infinite-dimensional data: global optimization guarantee in the mean-field regime

DOI10.1088/1742-5468/ad01b2MaRDI QIDQ6611443

Naoki Nishikawa, Atsushi Nitanda, Denny Wu, Taiji Suzuki

Publication date: 26 September 2024

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

zbMATH Keywords

learning theorymachine learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites Work

• Primal-dual subgradient methods for convex problems
• Functional multi-layer perceptron: A nonlinear tool for functional data analysis
• Optimal rates for the regularized least-squares algorithm
• Approximation of the invariant measure with an Euler scheme for stochastic PDEs driven by space-time white noise
• Duality and stability in extremum problems involving convex functions
• Weak approximation of stochastic partial differential equations: the nonlinear case
• Support Vector Machines
• Asymptotic evaluation of certain Markov process expectations for large time—III
• Nonparametric modelling for functional data: selected survey and tracks for future
• High-Dimensional Statistics
• Ergodicity for Infinite Dimensional Systems
• A mean field view of the landscape of two-layer neural networks
• Sampling can be faster than optimization
• Multilayer Perceptron with Functional Inputs: an Inverse Regression Approach
• NONPARAMETRIC REGRESSION ON FUNCTIONAL DATA: INFERENCE AND PRACTICAL ASPECTS
• Understanding Machine Learning

This page was built for publication: Two-layer neural network on infinite-dimensional data: global optimization guarantee in the mean-field regime