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. 2003.10576
13
13

Symmetry & critical points for a model shallow neural network

23 March 2020
Yossi Arjevani
M. Field
ArXivPDFHTML
Abstract

We consider the optimization problem associated with fitting two-layer ReLU networks with kkk hidden neurons, where labels are assumed to be generated by a (teacher) neural network. We leverage the rich symmetry exhibited by such models to identify various families of critical points and express them as power series in k−12k^{-\frac{1}{2}}k−21​. These expressions are then used to derive estimates for several related quantities which imply that not all spurious minima are alike. In particular, we show that while the loss function at certain types of spurious minima decays to zero like k−1k^{-1}k−1, in other cases the loss converges to a strictly positive constant. The methods used depend on symmetry, the geometry of group actions, bifurcation, and Artin's implicit function theorem.

View on arXiv
Comments on this paper