paper-with-me

Papers

Cryptographic Hardness of Learning Halfspaces with Massart Noise

2022-07-28 · Ilias Diakonikolas, Daniel M. Kane, Pasin Manurangsi, Lisheng Ren

We study the complexity of PAC learning halfspaces in the presence of Massart noise. In this problem, we are given i.i.d. labeled examples $(\mathbf{x}, y) \in \mathbb{R}^N \times \{ \pm 1\}$, where the distribution of $\mathbf{x}$ is arbitrary and the label $y$ is a Massart corruption of $f(\mathbf{x})$, for an unknown halfspace $f: \mathbb{R}^N \to \{ \pm 1\}$, with flipping probability $\eta(\mathbf{x}) \leq \eta < 1/2$. The goal of the learner is to compute a hypothesis with small 0-1 error. Our main result is the first computational hardness result for this learning problem. Specifically, assuming the (widely believed) subexponential-time hardness of the Learning with Errors (LWE) problem, we show that no polynomial-time Massart halfspace learner can achieve error better than $\Omega(\eta)$, even if the optimal 0-1 error is small, namely $\mathrm{OPT} = 2^{-\log^{c} (N)}$ for any universal constant $c \in (0, 1)$. Prior work had provided qualitatively similar evidence of hardness in the Statistical Query model. Our computational hardness result essentially resolves the polynomial PAC learnability of Massart halfspaces, by showing that known efficient learning algorithms for the problem are nearly best possible.

📄 PDF Abstract BibTeX arXiv:2207.14266

Code (0)

등록된 구현이 없습니다.

Tasks

PAC learning

Similar Papers 제목 키워드 기반

Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise

2020-12-17 · Ilias Diakonikolas, Daniel M. Kane

We study the problem of PAC learning halfspaces with Massart noise. Given labeled samples $(x, y)$ from a distribution $D$ on $\mathbb{R}^{d} \times \{ \pm 1\}$ such that the marginal $D_x$ on the examples is arbitrary a…

Learning TheoryPAC learning

Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noise

2021-02-10 · Chicheng Zhang, Yinan Li

We give a computationally-efficient PAC active learning algorithm for $d$-dimensional homogeneous halfspaces that can tolerate Massart noise (Massart and N\'ed\'elec, 2006) and Tsybakov noise (Tsybakov, 2004). Specialize…

Active Learning

Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random

2025-01-16 · Gautam Chandrasekaran, Vasilis Kontonis, Konstantinos Stavropoulos, Kevin Tian

We study the problem of PAC learning $\gamma$-margin halfspaces with Massart noise. We propose a simple proper learning algorithm, the Perspectron, that has sample complexity $\widetilde{O}((\epsilon\gamma)^{-2})$ and ac…

PAC learning

Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability

2020-12-01 · NeurIPS 2020 12 · Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau

In this paper, we revisit the problem of distribution-independently learning halfspaces under Massart noise with rate $\eta$. Recent work resolved a long-standing problem in this model of efficiently learning to error $\…

ClassificationFairnessGeneral ClassificationKnowledge Distillation

Testable Learning of General Halfspaces under Massart Noise

2026-02-25 · Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane, Sihan Liu arxiv

We study the algorithmic task of testably learning general Massart halfspaces under the Gaussian distribution. In the testable learning setting, the aim is the design of a tester-learner pair satisfying the following pro…