Saved in:
Bibliographic Details
Main Authors: Tang, Wenlu, Liu, Zicheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.05058
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916197465849856
author Tang, Wenlu
Liu, Zicheng
author_facet Tang, Wenlu
Liu, Zicheng
contents The performance of machine learning models can be impacted by changes in data over time. A promising approach to address this challenge is invariant learning, with a particular focus on a method known as invariant risk minimization (IRM). This technique aims to identify a stable data representation that remains effective with out-of-distribution (OOD) data. While numerous studies have developed IRM-based methods adaptive to data augmentation scenarios, there has been limited attention on directly assessing how well these representations preserve their invariant performance under varying conditions. In our paper, we propose a novel method to evaluate invariant performance, specifically tailored for IRM-based methods. We establish a bridge between the conditional expectation of an invariant predictor across different environments through the likelihood ratio. Our proposed criterion offers a robust basis for evaluating invariant performance. We validate our approach with theoretical support and demonstrate its effectiveness through extensive numerical studies.These experiments illustrate how our method can assess the invariant performance of various representation techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05058
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A robust assessment for invariant representations
Tang, Wenlu
Liu, Zicheng
Machine Learning
The performance of machine learning models can be impacted by changes in data over time. A promising approach to address this challenge is invariant learning, with a particular focus on a method known as invariant risk minimization (IRM). This technique aims to identify a stable data representation that remains effective with out-of-distribution (OOD) data. While numerous studies have developed IRM-based methods adaptive to data augmentation scenarios, there has been limited attention on directly assessing how well these representations preserve their invariant performance under varying conditions. In our paper, we propose a novel method to evaluate invariant performance, specifically tailored for IRM-based methods. We establish a bridge between the conditional expectation of an invariant predictor across different environments through the likelihood ratio. Our proposed criterion offers a robust basis for evaluating invariant performance. We validate our approach with theoretical support and demonstrate its effectiveness through extensive numerical studies.These experiments illustrate how our method can assess the invariant performance of various representation techniques.
title A robust assessment for invariant representations
topic Machine Learning
url https://arxiv.org/abs/2404.05058