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. 2107.10209
26
20

Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations

21 July 2021
Pranjal Awasthi
Alex K. Tang
Aravindan Vijayaraghavan
    MLT
ArXivPDFHTML
Abstract

We present polynomial time and sample efficient algorithms for learning an unknown depth-2 feedforward neural network with general ReLU activations, under mild non-degeneracy assumptions. In particular, we consider learning an unknown network of the form f(x)=aTσ(WTx+b)f(x) = {a}^{\mathsf{T}}\sigma({W}^\mathsf{T}x+b)f(x)=aTσ(WTx+b), where xxx is drawn from the Gaussian distribution, and σ(t):=max⁡(t,0)\sigma(t) := \max(t,0)σ(t):=max(t,0) is the ReLU activation. Prior works for learning networks with ReLU activations assume that the bias bbb is zero. In order to deal with the presence of the bias terms, our proposed algorithm consists of robustly decomposing multiple higher order tensors arising from the Hermite expansion of the function f(x)f(x)f(x). Using these ideas we also establish identifiability of the network parameters under minimal assumptions.

View on arXiv
Comments on this paper