Timezone: »

 
Poster
On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
Aaron Defazio · Leon Bottou

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #161
in Optimization -- Stochastic Optimization »

The application of stochastic variance reduction to optimization has shown remarkable recent theoretical and practical success. The applicability of these techniques to the hard non-convex optimization problems encountered during training of modern deep neural networks is an open problem. We show that naive application of the SVRG technique and related approaches fail, and explore why.

Keywords: Optimization for Deep Networks · Deep Learning
[ Paper]  [ Poster] 

Author Information

Aaron Defazio (Facebook AI Research)
Leon Bottou (FAIR)

More from the Same Authors