Research map / Optimization / Nonconvex and smooth optimization
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Riemannian SVRG instead of Riemannian stochastic gradient | Geodesically strongly convex finite-sum optimization · Geodesically strongly convex finite sums | convergence rate: O(1/t) | Helped |
| Use Riemannian SVRG instead of Riemannian SGD | Geodesically nonconvex finite-sum optimization · Geodesically nonconvex finite sums | IFO complexity: O(1/\epsilon^2); O\left(n + (n^{2/3}\zeta^{1/2}/\epsilon)\right) | Helped |
| Use Riemannian SVRG instead of Riemannian full gradient or stochastic gradient | Riemannian centroid computation · Riemannian centroid of PSD matrices | objective error | Helped |
| Use RSVRG instead of VR-PCA | Leading eigenvector computation · Leading eigenvector | IFO complexity | No clear effect |
| Increase inverse eigengap | RSVRG and VR-PCA · Leading eigenvector | estimated epochs to double accuracy | Hurt |
Closest papers by meaning
- SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization (ICML 2025 · similarity 0.93)
- Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds (NeurIPS 2025 · similarity 0.90)
- Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method (ICML 2025 · similarity 0.90)
- Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds (ICML 2024 · similarity 0.89)
- Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space (NeurIPS 2025 · similarity 0.89)
- Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point (ICML 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.