Saved in:
Bibliographic Details
Main Authors: Cohen, Khen, Levi, Noam, Oz, Yaron
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.18427
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914814979211264
author Cohen, Khen
Levi, Noam
Oz, Yaron
author_facet Cohen, Khen
Levi, Noam
Oz, Yaron
contents We derive closed-form expressions for the Bayes optimal decision boundaries in binary classification of high dimensional overlapping Gaussian mixture model (GMM) data, and show how they depend on the eigenstructure of the class covariances, for particularly interesting structured data. We empirically demonstrate, through experiments on synthetic GMMs inspired by real-world data, that deep neural networks trained for classification, learn predictors which approximate the derived optimal classifiers. We further extend our study to networks trained on authentic data, observing that decision thresholds correlate with the covariance eigenvectors rather than the eigenvalues, mirroring our GMM analysis. This provides theoretical insights regarding neural networks' ability to perform probabilistic inference and distill statistical patterns from intricate distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18427
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets
Cohen, Khen
Levi, Noam
Oz, Yaron
Machine Learning
Artificial Intelligence
We derive closed-form expressions for the Bayes optimal decision boundaries in binary classification of high dimensional overlapping Gaussian mixture model (GMM) data, and show how they depend on the eigenstructure of the class covariances, for particularly interesting structured data. We empirically demonstrate, through experiments on synthetic GMMs inspired by real-world data, that deep neural networks trained for classification, learn predictors which approximate the derived optimal classifiers. We further extend our study to networks trained on authentic data, observing that decision thresholds correlate with the covariance eigenvectors rather than the eigenvalues, mirroring our GMM analysis. This provides theoretical insights regarding neural networks' ability to perform probabilistic inference and distill statistical patterns from intricate distributions.
title Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.18427