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. 2304.10524
19
13

Learning Narrow One-Hidden-Layer ReLU Networks

20 April 2023
Sitan Chen
Zehao Dou
Surbhi Goel
Adam R. Klivans
Raghu Meka
    MLT
ArXivPDFHTML
Abstract

We consider the well-studied problem of learning a linear combination of kkk ReLU activations with respect to a Gaussian distribution on inputs in ddd dimensions. We give the first polynomial-time algorithm that succeeds whenever kkk is a constant. All prior polynomial-time learners require additional assumptions on the network, such as positive combining coefficients or the matrix of hidden weight vectors being well-conditioned. Our approach is based on analyzing random contractions of higher-order moment tensors. We use a multi-scale analysis to argue that sufficiently close neurons can be collapsed together, sidestepping the conditioning issues present in prior work. This allows us to design an iterative procedure to discover individual neurons.

View on arXiv
Comments on this paper