Document Type

Conference Proceeding

Publication Title

Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023

Abstract

This paper presents SVAM (Sequential Variance-Altered MLE), a unified framework for learning generalized linear models under adversarial label corruption in training data. SVAM extends to tasks such as least squares regression, logistic regression, and gamma regression, whereas many existing works on learning with label corruptions focus only on least squares regression. SVAM is based on a novel variance reduction technique that may be of independent interest and works by iteratively solving weighted MLEs over variance-altered versions of the GLM objective. SVAM offers provable model recovery guarantees superior to the state-of-the-art for robust regression even when a constant fraction of training labels are adversarially corrupted. SVAM also empirically outperforms several existing problem-specific techniques for robust regression and classification. Code for SVAM is available at https://github.com/purushottamkar/svam/.

First Page

9243

Last Page

9250

DOI

10.1609/aaai.v37i8.26108

Publication Date

6-27-2023

Keywords

ML, Learning Theory, ML, Adversarial Learning & Robustness, ML, Classification and Regression, ML, Optimization

Comments

Archived thanks to AAAI OJS

License: Open source publishing system

Uploaded 29 January 2024

Download

Share

COinS