Saved in:
Bibliographic Details
Main Authors: Zeng, Shiwei, Shen, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.21430
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915834527481856
author Zeng, Shiwei
Shen, Jie
author_facet Zeng, Shiwei
Shen, Jie
contents Attribute-efficient PAC learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning algorithms are faced with prevalent data corruptions or even malicious attacks. It is of central interest to design computationally-efficient algorithms that are robust to malicious corruptions. In this paper, we consider that there exists a constant amount of malicious noise in the data and the goal is to learn an underlying $s$-sparse halfspace $w^* \in \mathbb{R}^d$ with $\text{poly}(s,\log d)$ samples. Specifically, we follow a recent line of works and assume that the underlying distribution satisfies a certain concentration condition and a margin condition at the same time. Under such conditions, we show that attribute-efficiency can be achieved with simple variants to existing hinge loss minimization programs. Our key contribution includes: 1) an attribute-efficient PAC learning algorithm that works under a constant malicious noise rate; 2) a new gradient analysis that carefully handles the sparsity admitted constraints in hinge loss minimization program.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate
Zeng, Shiwei
Shen, Jie
Machine Learning
Attribute-efficient PAC learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning algorithms are faced with prevalent data corruptions or even malicious attacks. It is of central interest to design computationally-efficient algorithms that are robust to malicious corruptions. In this paper, we consider that there exists a constant amount of malicious noise in the data and the goal is to learn an underlying $s$-sparse halfspace $w^* \in \mathbb{R}^d$ with $\text{poly}(s,\log d)$ samples. Specifically, we follow a recent line of works and assume that the underlying distribution satisfies a certain concentration condition and a margin condition at the same time. Under such conditions, we show that attribute-efficiency can be achieved with simple variants to existing hinge loss minimization programs. Our key contribution includes: 1) an attribute-efficient PAC learning algorithm that works under a constant malicious noise rate; 2) a new gradient analysis that carefully handles the sparsity admitted constraints in hinge loss minimization program.
title Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate
topic Machine Learning
url https://arxiv.org/abs/2505.21430