Convergence of a multilayer perceptron to histogram-based Bayesian regression

DOI10.4213/RM10273EMaRDI QIDQ6848243zbMATH OpenFDO

Authors Nikita A. Eliseev, Andrey Perminov, Denis Turdakov

Publication date 6 March 2026

Published in Russian Mathematical Surveys (Search for Journal in Brave)

Full work available at URL https://doi.org/10.4213/RM10273E

zbMATH Keywords

asymptotic equivalenceBayesian classifierconsistencyhistogram-based regressionmultilayer perceptronpiecewise linear activation functionsrandom hyperplanesunary classificationVC dimension

Mathematics Subject Classification ID

Density estimation (62G07) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07) Pattern recognition, speech recognition (68T10)

Cites work

• Approximation by superpositions of a sigmoidal function
• Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
• Dimension reduction by random hyperplane tessellations
• Extrapolation of the Bayesian classifier with an unknown support of the two-class mixture distribution
• Histogram regression estimation using data-dependent partitions
• Introduction to Piecewise Differentiable Equations
• On continuous selections of polynomial functions
• On the number of regions of piecewise linear neural networks
• Phase retrieval from the magnitudes of affine linear measurements
• The zero set of a real analytic function
• Tight lower bounds on the VC-dimension of geometric set systems

This page was built for publication: Convergence of a multilayer perceptron to histogram-based Bayesian regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6848243)