Research map / Optimization / Nonconvex and smooth optimization
Efficiently escaping saddle points on 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 |
|---|---|---|---|
| Separate steps on the manifold from perturbed gradient steps in a tangent space | Riemannian optimization · Riemannian manifolds | gradient queries: O((\log{d})^4 / \epsilon^{2}) | Helped |
| Use tangent-space steps on the pullback after perturbing | PRGD · Riemannian manifolds | fraction of visited points satisfying the second-order condition: at least two-thirds | Helped |
Closest papers by meaning
- Escaping from saddle points on Riemannian manifolds (NeurIPS 2019 · similarity 0.93)
- Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point (ICML 2024 · similarity 0.88)
- Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms (ICML 2024 · similarity 0.87)
- Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds (ICML 2024 · similarity 0.87)
- Riemannian coordinate descent algorithms on matrix manifolds (ICML 2024 · similarity 0.87)
- Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space (NeurIPS 2025 · similarity 0.87)
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.