Research map / Optimization / Nonconvex and smooth optimization
Faster First-Order Methods for Stochastic Non-Convex Optimization on Riemannian Manifolds
Pan Zhou, Xiao–Tong Yuan, Shuicheng Yan, Jiashi Feng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add gradient normalization and SPIDER recursive estimator (R-SPIDER) versus R-SGD, R-SVRG, R-SRG, R-SRG+ | R-SPIDER · k-PCA (Grassmann manifold) | sub-optimality vs IFO | Improved |
| add decaying aggressive learning rate (R-SPIDER-A) to R-SPIDER (ablation) | R-SPIDER · k-PCA (Grassmann manifold) | sub-optimality vs IFO | Improved |
| add adaptive learning rate to R-SRG and R-SRG+ baselines (ablation) | R-SRG · k-PCA (Grassmann manifold) | sub-optimality vs IFO | Improved |
| R-SPIDER-A versus R-SRG-A and R-SRG+A, all with adaptive learning rates | R-SPIDER-A · k-PCA (Grassmann manifold) | sub-optimality vs IFO | Improved |
| R-SPIDER-A and R-SPIDER versus baselines on low-rank matrix completion | R-SPIDER-A · Low-rank matrix completion (YaleB, AR, PIE, MovieLens-1M) | sub-optimality vs epochs | Improved |
Closest papers by meaning
- Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds (NeurIPS 2025 · similarity 0.91)
- SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization (ICML 2025 · similarity 0.91)
- Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method (ICML 2025 · similarity 0.89)
- Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds (ICML 2024 · similarity 0.89)
- Decentralized Projected Riemannian Stochastic Recursive Momentum Method for Nonconvex Optimization (AAAI 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.
