Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
–Neural Information Processing Systems
We study optimization of finite sums of \emph{geodesically} smooth functions on Riemannian manifolds. Although variance reduction techniques for optimizing finite-sums have witnessed tremendous attention in the recent years, existing work is limited to vector space problems. We introduce \emph{Riemannian SVRG} (\rsvrg), a new variance reduced Riemannian optimization method.
Neural Information Processing Systems
Nov-21-2025, 15:06:09 GMT
- Technology: