AI Paper Atlas

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

JMLR 2022 · Optimization › Nonconvex and smooth optimization · approach: Saddle-point escape algorithms · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
use R-ProxSPB instead of SPAMS for online sparse PCAonline sparse PCA · coil100sparsity (nonzeros): 240 -> 22Improved
use R-ProxSPB instead of SPAMS for online sparse PCAonline sparse PCA · mnistsparsity (nonzeros): 185 -> 18Improved
use R-ProxSPB instead of SPAMS for online sparse PCAonline sparse PCA · coil100explained variance: 0.0132 -> 0.0120No clear effect
use R-ProxSPB instead of SPAMS for online sparse PCAonline sparse PCA · mnistexplained variance: 0.0179 -> 0.0190No clear effect
add variance-reduced R-SARAH estimator (R-ProxSPB) over plain minibatch R-ProxSGDRiemannian proximal stochastic gradient · online sparse PCA, mnist and coil100loss valueImproved
use proximal methods (R-ProxSGD, R-ProxSPB) instead of Riemannian subgradientonline sparse PCA · mnist and coil100loss value vs CPU time and IFOImproved
use stochastic methods instead of deterministic ManPGonline sparse PCA · mnist and coil100loss value at same budgetImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy