Saved in:
Bibliographic Details
Main Authors: Yang, Zijian, Eminyan, Vahe, Schlüter, Ralf, Ney, Hermann
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.01309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909322786635776
author Yang, Zijian
Eminyan, Vahe
Schlüter, Ralf
Ney, Hermann
author_facet Yang, Zijian
Eminyan, Vahe
Schlüter, Ralf
Ney, Hermann
contents In statistical classification/multiple hypothesis testing and machine learning, a model distribution estimated from the training data is usually applied to replace the unknown true distribution in the Bayes decision rule, which introduces a mismatch between the Bayes error and the model-based classification error. In this work, we derive the classification error bound to study the relationship between the Kullback-Leibler divergence and the classification error mismatch. We first reconsider the statistical bounds based on classification error mismatch derived in previous works, employing a different method of derivation. Then, motivated by the observation that the Bayes error is typically low in machine learning tasks like speech recognition and pattern recognition, we derive a refined Kullback-Leibler-divergence-based bound on the error mismatch with the constraint that the Bayes error is lower than a threshold.
format Preprint
id arxiv_https___arxiv_org_abs_2409_01309
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Refined Statistical Bounds for Classification Error Mismatches with Constrained Bayes Error
Yang, Zijian
Eminyan, Vahe
Schlüter, Ralf
Ney, Hermann
Information Theory
In statistical classification/multiple hypothesis testing and machine learning, a model distribution estimated from the training data is usually applied to replace the unknown true distribution in the Bayes decision rule, which introduces a mismatch between the Bayes error and the model-based classification error. In this work, we derive the classification error bound to study the relationship between the Kullback-Leibler divergence and the classification error mismatch. We first reconsider the statistical bounds based on classification error mismatch derived in previous works, employing a different method of derivation. Then, motivated by the observation that the Bayes error is typically low in machine learning tasks like speech recognition and pattern recognition, we derive a refined Kullback-Leibler-divergence-based bound on the error mismatch with the constraint that the Bayes error is lower than a threshold.
title Refined Statistical Bounds for Classification Error Mismatches with Constrained Bayes Error
topic Information Theory
url https://arxiv.org/abs/2409.01309