Weak error analysis for stochastic gradient descent via diffusion approximation

Probability and Financial Mathematics Seminar

Meeting Details

For more information about this meeting, contact Kristin Berrigan, Anna Mazzucato, Alexei Novikov, Yuanyuan Feng.

Speaker: Yuanyuan Feng, Penn State

Abstract: I will talk about diffusion approximation to stochastic gradient descent algorithms. We prove that diffusion approximation provides weak approximation for stochastic gradient descent algorithms in a finite time horizon. We then introduce new tools motivated by the backward error analysis of numerical stochastic differential equations into the theoretical framework of diffusion approximation, extending the validity of the weak approximation from finite to infinite time horizon.


Room Reservation Information

Room Number: 114 McAllister

Date: 10/04/2019

Time: 2:30pm - 4:30pm