Saved in:
Bibliographic Details
Main Authors: Clara, Gabriel, Langer, Sophie, Schmidt-Hieber, Johannes
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.10529
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We investigate the statistical behavior of gradient descent iterates with dropout in the linear regression model. In particular, non-asymptotic bounds for the convergence of expectations and covariance matrices of the iterates are derived. The results shed more light on the widely cited connection between dropout and l2-regularization in the linear model. We indicate a more subtle relationship, owing to interactions between the gradient descent dynamics and the additional randomness induced by dropout. Further, we study a simplified variant of dropout which does not have a regularizing effect and converges to the least squares estimator