Saved in:
Bibliographic Details
Main Authors: Zhou, Tian-Yi, Lau, Matthew, Chen, Jizhou, Lee, Wenke, Huo, Xiaoming
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.08521
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912025886588928
author Zhou, Tian-Yi
Lau, Matthew
Chen, Jizhou
Lee, Wenke
Huo, Xiaoming
author_facet Zhou, Tian-Yi
Lau, Matthew
Chen, Jizhou
Lee, Wenke
Huo, Xiaoming
contents Anomaly detection is an important problem in many application areas, such as network security. Many deep learning methods for unsupervised anomaly detection produce good empirical performance but lack theoretical guarantees. By casting anomaly detection into a binary classification problem, we establish non-asymptotic upper bounds and a convergence rate on the excess risk on rectified linear unit (ReLU) neural networks trained on synthetic anomalies. Our convergence rate on the excess risk matches the minimax optimal rate in the literature. Furthermore, we provide lower and upper bounds on the number of synthetic anomalies that can attain this optimality. For practical implementation, we relax some conditions to improve the search for the empirical risk minimizer, which leads to competitive performance to other classification-based methods for anomaly detection. Overall, our work provides the first theoretical guarantees of unsupervised neural network-based anomaly detectors and empirical insights on how to design them well.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08521
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Optimal Classification-based Anomaly Detection with Neural Networks: Theory and Practice
Zhou, Tian-Yi
Lau, Matthew
Chen, Jizhou
Lee, Wenke
Huo, Xiaoming
Machine Learning
Cryptography and Security
Statistics Theory
Anomaly detection is an important problem in many application areas, such as network security. Many deep learning methods for unsupervised anomaly detection produce good empirical performance but lack theoretical guarantees. By casting anomaly detection into a binary classification problem, we establish non-asymptotic upper bounds and a convergence rate on the excess risk on rectified linear unit (ReLU) neural networks trained on synthetic anomalies. Our convergence rate on the excess risk matches the minimax optimal rate in the literature. Furthermore, we provide lower and upper bounds on the number of synthetic anomalies that can attain this optimality. For practical implementation, we relax some conditions to improve the search for the empirical risk minimizer, which leads to competitive performance to other classification-based methods for anomaly detection. Overall, our work provides the first theoretical guarantees of unsupervised neural network-based anomaly detectors and empirical insights on how to design them well.
title Optimal Classification-based Anomaly Detection with Neural Networks: Theory and Practice
topic Machine Learning
Cryptography and Security
Statistics Theory
url https://arxiv.org/abs/2409.08521