New framework for convex optimization on Riemannian manifolds introduced

Researchers have developed a new framework for convex optimization on Riemannian manifolds, introducing concepts of retraction-specific convex sets and retraction-based gradient projection algorithms. This framework extends the standard gradient projection algorithms and includes convergence proofs for various stepsize rules. The approach has been applied to weighted low-rank approximation and numerically validated on an image completion task. AI

RANK_REASON The item is an academic paper submitted to arXiv detailing a new mathematical framework and its applications. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• arXivLabs
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Gradient Projection Algorithms and Software for Arbitrary Rotation Criteria in Factor Analysis
• Hugging Face
• image completion task
• Influence Flower
• Litmaps
• Retraction-Based Gradient Projection Algorithms on Manifolds
• Riemannian manifold
• ScienceCast
• scite Smart Citations
• weighted low-rank approximation

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →