AI RESEARCH
A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints
arXiv CS.LG
•
ArXi:2304.03641v4 Announce Type: replace-cross Nonsmooth composite optimization with orthogonality constraints has a wide range of applications in statistical learning and data science. However, this problem is challenging due to its nonsmooth objective and computationally expensive nonconvex constraints. In this paper, we propose a new approach called \textbf{OBCD}, which leverages block coordinate descent to address these challenges. \textbf{OBCD} is a feasible method with a small computational footprint.