ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1906.10075
30
80

Distribution-Independent PAC Learning of Halfspaces with Massart Noise

24 June 2019
Ilias Diakonikolas
Themis Gouleakis
Christos Tzamos
ArXivPDFHTML
Abstract

We study the problem of {\em distribution-independent} PAC learning of halfspaces in the presence of Massart noise. Specifically, we are given a set of labeled examples (x,y)(\mathbf{x}, y)(x,y) drawn from a distribution D\mathcal{D}D on Rd+1\mathbb{R}^{d+1}Rd+1 such that the marginal distribution on the unlabeled points x\mathbf{x}x is arbitrary and the labels yyy are generated by an unknown halfspace corrupted with Massart noise at noise rate η<1/2\eta<1/2η<1/2. The goal is to find a hypothesis hhh that minimizes the misclassification error Pr(x,y)∼D[h(x)≠y]\mathbf{Pr}_{(\mathbf{x}, y) \sim \mathcal{D}} \left[ h(\mathbf{x}) \neq y \right]Pr(x,y)∼D​[h(x)=y]. We give a poly(d,1/ϵ)\mathrm{poly}\left(d, 1/\epsilon \right)poly(d,1/ϵ) time algorithm for this problem with misclassification error η+ϵ\eta+\epsilonη+ϵ. We also provide evidence that improving on the error guarantee of our algorithm might be computationally hard. Prior to our work, no efficient weak (distribution-independent) learner was known in this model, even for the class of disjunctions. The existence of such an algorithm for halfspaces (or even disjunctions) has been posed as an open question in various works, starting with Sloan (1988), Cohen (1997), and was most recently highlighted in Avrim Blum's FOCS 2003 tutorial.

View on arXiv
Comments on this paper