Skip to yearly menu bar Skip to main content


Poster

Acceleration and Implicit Regularization in Gaussian Phase Retrieval

Tyler Maunu · Martin Molina-Fructuoso

MR1 & MR2 - Number 134
[ ]
Sat 4 May 6 a.m. PDT — 8:30 a.m. PDT

Abstract:

We study accelerated optimization methods in the Gaussian phase retrieval problem. In this setting, we prove that gradient methods with Polyak or Nesterov momentum have similar implicit regularization to gradient descent. This implicit regularization ensures that the algorithms remain in a nice region, where the cost function is strongly convex and smooth despite being nonconvex in general. This ensures that these accelerated methods achieve faster rates of convergence than gradient descent. Experimental evidence demonstrates that the accelerated methods converge faster than gradient descent in practice.

Live content is unavailable. Log in and register to view live content