Concentration of measure and global optimization of Bayesian multilayer perceptron. I

DOI10.1134/S1995080224600651MaRDI QIDQ6586789zbMATH OpenFDO

Authors B. K. Temyanov, R. R. Nigmatullin

Publication date 13 August 2024

Published in Lobachevskii Journal of Mathematics (Search for Journal in Brave)

zbMATH Keywords

Jacobianconcentration of measureBayesian neural networkquasi-spherical coordinate system

Mathematics Subject Classification ID

Bayesian inference (62F15) Normed linear spaces and Banach spaces; Banach lattices (46Bxx)

Recommendations

• Global minima of overparameterized neural networks
• Approximation of classifiers by deep perceptron networks
• A global universality of two-layer neural networks with ReLU activations
• Measure concentration in optimization
• Gradient descent on infinitely wide neural networks: global convergence and generalization

Cites work

• scientific article; zbMATH DE number 4115283 (Why is no real title available?)
• scientific article; zbMATH DE number 3374069 (Why is no real title available?)
• Asymptotic geometric analysis. Part II
• Bayesian methods for neural networks and related models
• Bayesian neural networks: an introduction and survey
• Stochastic neural networks
• Variational Bayesian Inference for a Nonlinear Forward Model

This page was built for publication: Concentration of measure and global optimization of Bayesian multilayer perceptron. I

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6586789)