[iasmath-semru] [math-ias] Reminder: Members' Seminar--Monday, April 2, 2018

[Kristina Phillips]

INSTITUTE FOR ADVANCED STUDY
School of Mathematics
Princeton, NJ 08540
 
Members' Seminar
Monday, April 2
 
 
Topic:                     On Expressiveness and Optimization in Deep
Learning
Speaker:                 Nadav Cohen, Member, School of Mathematics
Time/Room:           2:00pm - 3:00pm/Simonyi Hall 101
Abstract Link:
http://www.math.ias.edu/seminars/abstract?event=129359

 

Three fundamental factors determine the quality of a statistical learning
algorithm: expressiveness, optimization and generalization. The classic
strategy for handling these factors is relatively well understood. In
contrast, the radically different approach of deep learning, which in the
last few years has revolutionized the world of artificial intelligence, is
shrouded by mystery. This talk will describe a series of works aimed at
unraveling some of the mysteries behind expressiveness and optimization. I
will begin by establishing an equivalence between convolutional networks -
the most successful deep learning architecture to date, and hierarchical
tensor decompositions. The equivalence will be used to answer various
questions concerning the expressiveness of convolutional networks. I will
then turn to discuss recent work analyzing optimization of deep linear
networks. Surprisingly, in stark contrast with conventional wisdom, we find
that depth, despite its non-convex nature, can accelerate optimization.

 

 

 

 

 

-----------------------------------------

http://www.math.ias.edu/seminars

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://imap.math.ias.edu/pipermail/iasmathsemrutgers/attachments/20180402/77f45e98/attachment.html>