Research map / Optimization / Nonconvex and smooth optimization
Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold
Bokun Wang, Shiqian Ma, Lingzhou Xue
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 |
|---|---|---|---|
| use R-ProxSPB instead of SPAMS for online sparse PCA | online sparse PCA · coil100 | sparsity (nonzeros): 240 -> 22 | Improved |
| use R-ProxSPB instead of SPAMS for online sparse PCA | online sparse PCA · mnist | sparsity (nonzeros): 185 -> 18 | Improved |
| use R-ProxSPB instead of SPAMS for online sparse PCA | online sparse PCA · coil100 | explained variance: 0.0132 -> 0.0120 | No clear effect |
| use R-ProxSPB instead of SPAMS for online sparse PCA | online sparse PCA · mnist | explained variance: 0.0179 -> 0.0190 | No clear effect |
| add variance-reduced R-SARAH estimator (R-ProxSPB) over plain minibatch R-ProxSGD | Riemannian proximal stochastic gradient · online sparse PCA, mnist and coil100 | loss value | Improved |
| use proximal methods (R-ProxSGD, R-ProxSPB) instead of Riemannian subgradient | online sparse PCA · mnist and coil100 | loss value vs CPU time and IFO | Improved |
| use stochastic methods instead of deterministic ManPG | online sparse PCA · mnist and coil100 | loss value at same budget | Improved |
Closest papers by meaning
- Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds (ICML 2024 · similarity 0.91)
- Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point (ICML 2024 · similarity 0.91)
- SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization (ICML 2025 · similarity 0.91)
- 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)
- Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms (ICML 2024 · similarity 0.89)
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.
