@kirk86

Shape Matters: Understanding the Implicit Bias of the Noise Covariance

, , , and . (2020)cite arxiv:2006.08680.

Abstract

The noise in stochastic gradient descent (SGD) provides a crucial implicit regularization effect for training overparameterized models. Prior theoretical work largely focuses on spherical Gaussian noise, whereas empirical studies demonstrate the phenomenon that parameter-dependent noise -- induced by mini-batches or label perturbation -- is far more effective than Gaussian noise. This paper theoretically characterizes this phenomenon on a quadratically-parameterized model introduced by Vaskevicius et el. and Woodworth et el. We show that in an over-parameterized setting, SGD with label noise recovers the sparse ground-truth with an arbitrary initialization, whereas SGD with Gaussian noise or gradient descent overfits to dense solutions with large norms. Our analysis reveals that parameter-dependent noise introduces a bias towards local minima with smaller noise variance, whereas spherical Gaussian noise does not. Code for our project is publicly available.

Description

[2006.08680] Shape Matters: Understanding the Implicit Bias of the Noise Covariance

Links and resources

Tags

community

  • @kirk86
  • @dblp
@kirk86's tags highlighted