paper-with-me

Papers

Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate

2024-10-02 · Jie Shen

Understanding noise tolerance of machine learning algorithms is a central quest in learning theory. In this work, we study the problem of computationally efficient PAC learning of halfspaces in the presence of malicious noise, where an adversary can corrupt both instances and labels of training samples. The best-known noise tolerance either depends on a target error rate under distributional assumptions or on a margin parameter under large-margin conditions. In this work, we show that when both types of conditions are satisfied, it is possible to achieve constant noise tolerance by minimizing a reweighted hinge loss. Our key ingredients include: 1) an efficient algorithm that finds weights to control the gradient deterioration from corrupted samples, and 2) a new analysis on the robustness of the hinge loss equipped with such weights.

📄 PDF Abstract BibTeX arXiv:2410.01186

Code (0)

등록된 구현이 없습니다.

Tasks

Learning TheoryPAC learning

Similar Papers 제목 키워드 기반

Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate

2025-05-27 · Shiwei Zeng, Jie Shen

Attribute-efficient 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 adversarial atta…

AttributeLearning TheoryPAC learning

Learning large-margin halfspaces with more malicious noise

2011-12-01 · NeurIPS 2011 12 · Phil Long, Rocco Servedio

We describe a simple algorithm that runs in time poly(n,1/gamma,1/eps) and learns an unknown n-dimensional gamma-margin halfspace to accuracy 1-eps in the presence of malicious noise, when the noise rate is allowed to…

Attribute-Efficient Learning of Halfspaces with Malicious Noise: Near-Optimal Label Complexity and Noise Tolerance

2020-06-06 · Jie Shen, Chicheng Zhang

This paper is concerned with computationally efficient learning of homogeneous sparse halfspaces in $\mathbb{R}^d$ under noise. Though recent works have established attribute-efficient learning algorithms under various t…

Active LearningAttributeOpen-Ended Question Answering

Sample-Optimal PAC Learning of Halfspaces with Malicious Noise

2021-02-11 · Jie Shen

We study efficient PAC learning of homogeneous halfspaces in $\mathbb{R}^d$ in the presence of malicious noise of Valiant (1985). This is a challenging noise model and only until recently has near-optimal noise tolerance…

PAC learning

Learning Geometric Concepts with Nasty Noise

2017-07-05 · Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart

We study the efficient learnability of geometric concept classes - specifically, low-degree polynomial threshold functions (PTFs) and intersections of halfspaces - when a fraction of the data is adversarially corrupted. …

LEMMAOutlier DetectionPAC learning