Riemannian stochastic recursive momentum method for non-convex optimization

We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a near-optimal complexity of tildeO(ε-3) to find ε-approximate solution with one sample. That is, our method requires 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.