Riemannian Stochastic Hybrid Gradient Algorithm for Nonconvex Optimization

Abstract

In recent years, Riemannian stochastic gradient descent (R-SGD), Riemannian stochastic variance reduction (R-SVRG) and Riemannian stochastic recursive gradient (R-SRG) have attracted considerable attention on Riemannian optimization. Under normal circumstances, it is impossible to analyze the convergence of R-SRG algorithm alone. The main reason is that the conditional expectation of the descending direction is a biased estimation. However, in this paper, we consider linear combination of three descent directions on Riemannian manifolds as the new descent direction (i.e., R-SRG, R-SVRG and R-SGD) and the parameters are time-varying. At first, we propose a Riemannian stochastic hybrid gradient(R-SHG) algorithm with adaptive parameters. The algorithm gets a global convergence analysis with a decaying step size. For the case of step-size is fixed, we consider two cases with the inner loop fixed and time-varying. Meanwhile, we quantitatively research the convergence speed of the algorithm. Since the global convergence of the R-SHG algorithm with adaptive parameters requires higher functional differentiability, we propose a R-SHG algorithm with time-varying parameters. And we obtain similar conclusions under weaker conditions.

References in corpus (5)

• Manopt, a Matlab toolbox for optimization on manifolds
• Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region Method
• Low-rank tensor completion: a Riemannian manifold preconditioning approach
• Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
• Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport