Learning one-hidden-layer neural networks with landscape design

Rong Ge, Jason D. Lee, Tengyu Ma

Research output: Contribution to conferencePaperpeer-review

76 Scopus citations

Abstract

We consider the problem of learning a one-hidden-layer neural network: we assume the input x ∈ Rd is from Gaussian distribution and the label y = a>σ(Bx) + ξ, where a is a nonnegative vector in Rm with m ≤ d, B ∈ Rm×d is a full-rank weight matrix, and ξ is a noise vector. We first give an analytic formula for the population risk of the standard squared loss and demonstrate that it implicitly attempts to decompose a sequence of low-rank tensors simultaneously. Inspired by the formula, we design a non-convex objective function G(•) whose landscape is guaranteed to have the following properties: 1. All local minima of G are also global minima. 2. All global minima of G correspond to the ground truth parameters. 3. The value and gradient of G can be estimated using samples. With these properties, stochastic gradient descent on G provably converges to the global minimum and learn the ground-truth parameters. We also prove finite sample complexity results and validate the results by simulations.

Original languageEnglish (US)
StatePublished - 2018
Externally publishedYes
Event6th International Conference on Learning Representations, ICLR 2018 - Vancouver, Canada
Duration: Apr 30 2018May 3 2018

Conference

Conference6th International Conference on Learning Representations, ICLR 2018
Country/TerritoryCanada
CityVancouver
Period4/30/185/3/18

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Education
  • Computer Science Applications
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Learning one-hidden-layer neural networks with landscape design'. Together they form a unique fingerprint.

Cite this