2000 character limit reached
Riemannian stochastic recursive momentum method for non-convex optimization (2008.04555v1)
Published 11 Aug 2020 in math.OC, cs.LG, and stat.ML
Abstract: We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a near-optimal complexity of $\tilde{\mathcal{O}}(\epsilon{-3})$ to find $\epsilon$-approximate solution with one sample. That is, our method requires $\mathcal{O}(1)$ gradient evaluations per iteration and does not require restarting with a large batch gradient, which is commonly used to obtain the faster rate. Extensive experiment results demonstrate the superiority of our proposed algorithm.