Stochastic variance reduction for nonconvex optimization
International conference on machine learning, 2016•proceedings.mlr.press
We study nonconvex finite-sum problems and analyze stochastic variance reduced gradient
(SVRG) methods for them. SVRG and related methods have recently surged into
prominence for convex optimization given their edge over stochastic gradient descent
(SGD); but their theoretical analysis almost exclusively assumes convexity. In contrast, we
prove non-asymptotic rates of convergence (to stationary points) of SVRG for nonconvex
optimization, and show that it is provably faster than SGD and gradient descent. We also …
(SVRG) methods for them. SVRG and related methods have recently surged into
prominence for convex optimization given their edge over stochastic gradient descent
(SGD); but their theoretical analysis almost exclusively assumes convexity. In contrast, we
prove non-asymptotic rates of convergence (to stationary points) of SVRG for nonconvex
optimization, and show that it is provably faster than SGD and gradient descent. We also …
Abstract
We study nonconvex finite-sum problems and analyze stochastic variance reduced gradient (SVRG) methods for them. SVRG and related methods have recently surged into prominence for convex optimization given their edge over stochastic gradient descent (SGD); but their theoretical analysis almost exclusively assumes convexity. In contrast, we prove non-asymptotic rates of convergence (to stationary points) of SVRG for nonconvex optimization, and show that it is provably faster than SGD and gradient descent. We also analyze a subclass of nonconvex problems on which SVRG attains linear convergence to the global optimum. We extend our analysis to mini-batch variants of SVRG, showing (theoretical) linear speedup due to minibatching in parallel settings.
proceedings.mlr.press