Statistical Inference for Autoencoder-based Anomaly Detection after Representation Learning-based Domain Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kiet, Tran Tuan, Loi, Nguyen Thang, Duy, Vo Nguyen Le
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911100517220352
author Kiet, Tran Tuan
Loi, Nguyen Thang
Duy, Vo Nguyen Le
author_facet Kiet, Tran Tuan
Loi, Nguyen Thang
Duy, Vo Nguyen Le
contents Anomaly detection (AD) plays a vital role across a wide range of domains, but its performance might deteriorate when applied to target domains with limited data. Domain Adaptation (DA) offers a solution by transferring knowledge from a related source domain with abundant data. However, this adaptation process can introduce additional uncertainty, making it difficult to draw statistically valid conclusions from AD results. In this paper, we propose STAND-DA -- a novel framework for statistically rigorous Autoencoder-based AD after Representation Learning-based DA. Built on the Selective Inference (SI) framework, STAND-DA computes valid $p$-values for detected anomalies and rigorously controls the false positive rate below a pre-specified level $α$ (e.g., 0.05). To address the computational challenges of applying SI to deep learning models, we develop the GPU-accelerated SI implementation, significantly enhancing both scalability and runtime performance. This advancement makes SI practically feasible for modern, large-scale deep architectures. Extensive experiments on synthetic and real-world datasets validate the theoretical results and computational efficiency of the proposed STAND-DA method.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Statistical Inference for Autoencoder-based Anomaly Detection after Representation Learning-based Domain Adaptation
Kiet, Tran Tuan
Loi, Nguyen Thang
Duy, Vo Nguyen Le
Machine Learning
Anomaly detection (AD) plays a vital role across a wide range of domains, but its performance might deteriorate when applied to target domains with limited data. Domain Adaptation (DA) offers a solution by transferring knowledge from a related source domain with abundant data. However, this adaptation process can introduce additional uncertainty, making it difficult to draw statistically valid conclusions from AD results. In this paper, we propose STAND-DA -- a novel framework for statistically rigorous Autoencoder-based AD after Representation Learning-based DA. Built on the Selective Inference (SI) framework, STAND-DA computes valid $p$-values for detected anomalies and rigorously controls the false positive rate below a pre-specified level $α$ (e.g., 0.05). To address the computational challenges of applying SI to deep learning models, we develop the GPU-accelerated SI implementation, significantly enhancing both scalability and runtime performance. This advancement makes SI practically feasible for modern, large-scale deep architectures. Extensive experiments on synthetic and real-world datasets validate the theoretical results and computational efficiency of the proposed STAND-DA method.
title Statistical Inference for Autoencoder-based Anomaly Detection after Representation Learning-based Domain Adaptation
topic Machine Learning
url https://arxiv.org/abs/2508.07049