Adaptive Stochastic Gradient Descents on Manifolds with an Application on Weighted Low-Rank Approximation

We prove a convergence theorem for stochastic gradient descents on manifolds with adaptive learning rate and apply it to the weighted low-rank approximation problem.

math.OC cs.AI cs.LG Mathematics Computer Science

View graph Source

Paper

Similar papers

Weighted Low-rank Approximation via Stochastic Gradient Descent on ManifoldsConglong Xu, Peiqi Yang, Hao Wu2025 · 0 citations In Library

Convergence of Gradient Descent for Low-Rank Matrix ApproximationRenaud-Alexandre Pitaval, Wei Dai, O. Tirkkonen2015 · IEEE Transactions on Information Theory · 21 citations In Library

Riemannian adaptive stochastic gradient algorithms on matrix manifoldsHiroyuki Kasai, Pratik Jawanpuria, Bamdev Mishra2019 · International Conference on Machine Learning · 3 citations In Library

Stochastic gradient descent on Riemannian manifoldsS. Bonnabel2011 · IEEE Transactions on Automatic Control · 716 citations In Library

Averaging Stochastic Gradient Descent on Riemannian ManifoldsNilesh Tripuraneni, Nicolas Flammarion, F. Bach et al.2018 · Annual Conference Computational Learning Theory · 114 citations In Library

Generalized Steepest Descent Methods on Riemannian Manifolds and Hilbert Spaces: Convergence Analysis and Stochastic ExtensionsH.A. Abdul-Rashid, Samad, Amal A2025 · arXiv (Cornell University) In Library

Adaptive Single-Loop Methods for Stochastic Minimax Optimization on Riemannian ManifoldsHongye Wang, He Chang, Bo Jiang2026 · Open MIND In Library

Learning-Rate-Free Stochastic Optimization over Riemannian ManifoldsDaniel Dodd, Louis Sharrock, Christopher Nemeth2024 · arXiv (Cornell University) · 2 citations In Library

Decentralized Riemannian Gradient Descent on the Stiefel ManifoldShixiang Chen, Alfredo García, Mingyi Hong et al.2021 · International Conference on Machine Learning · 67 citations In Library

Gradient Descent Ascent for Minimax Problems on Riemannian ManifoldsFeihu Huang, Shangqian Gao, Heng Huang2021 · arXiv (Cornell University) · 40 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal