[Colloquium] 8/15 Thesis Defense: Behnam Neyshabur, TTIC

[Mary Marre via Colloquium]

When:    Tuesday, August 15th at 1:00 pm

Where:   TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:      Behnam Neyshabur, TTIC


Title:       Implicit Regularization in Deep Learning

Abstract:
In an attempt to better understand generalization in deep learning, I
explore several possible explanations. I explain why implicit
regularization induced by the optimization method is playing a key role in
generalization and success of deep learning models. Motivated by this view,
I discuss how different complexity measures can ensure generalization and
explain how optimization algorithms can implicitly regularize complexity
measures. I empirically investigate the ability of these measures to
explain different observed phenomena in deep learning. I further discuss
the invariances in neural networks, suggest complexity measures and
optimization algorithms that have similar invariances to those in neural
networks and evaluate them on a number of learning tasks.

Thesis Advisor: Nati Srebro <nati at ttic.edu>



Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20170814/60f27379/attachment.html>