MADMM: A Generic Algorithm for Non-smooth Optimization on Manifolds

Abstract

Numerous problems in machine learning are formulated as optimization with manifold constraints. In this paper, we propose the Manifold alternating directions method of multipliers (MADMM), an extension of the classical ADMM scheme for manifold-constrained non-smooth optimization problems and show its application to several challenging problems in… (More)
DOI: 10.1007/978-3-319-46454-1_41

Topics

6 Figures and Tables

Statistics

020406080201520162017
Citations per Year

Citation Velocity: 20

Averaging 20 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Blog articles referencing this paper

Slides referencing similar topics