On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
This addresses the challenge of efficient optimization for deep neural networks, but the findings are incremental as they highlight limitations rather than propose a new solution.
The paper tackled the problem of applying stochastic variance reduction techniques to non-convex deep learning optimization, finding that naive implementations like SVRG fail in this context.
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.