A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network

Mo Zhou, Rong Ge, Chi Jin

Research output: Contribution to journalConference articlepeer-review

11 Scopus citations

Abstract

While over-parameterization is widely believed to be crucial for the success of optimization for the neural networks, most existing theories on over-parameterization do not fully explain the reason—they either work in the Neural Tangent Kernel regime where neurons don’t move much, or require an enormous number of neurons. In practice, when the data is generated using a teacher neural network, even mildly over-parameterized neural networks can achieve 0 loss and recover the directions of teacher neurons. In this paper we develop a local convergence theory for mildly over-parameterized two-layer neural net. We show that as long as the loss is already lower than a threshold (polynomial in relevant parameters), all student neurons in an over-parameterized two-layer neural network will converge to one of teacher neurons, and the loss will go to 0. Our result holds for any number of student neurons as long as it is at least as large as the number of teacher neurons, and our convergence rate is independent of the number of student neurons. A key component of our analysis is the new characterization of local optimization landscape—we show the gradient satisfies a special case of Lojasiewicz property which is different from local strong convexity or PL conditions used in previous work.

Original languageEnglish (US)
Pages (from-to)4577-4632
Number of pages56
JournalProceedings of Machine Learning Research
Volume134
StatePublished - 2021
Event34th Conference on Learning Theory, COLT 2021 - Boulder, United States
Duration: Aug 15 2021Aug 19 2021

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network'. Together they form a unique fingerprint.

Cite this