A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions

Quoc Tran-Dinh, Anastasios T. Kyrillidis, Volkan Cevher. A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions. In Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16-21 June 2013. Volume 28 of JMLR Proceedings, pages 271-279, JMLR.org, 2013. [doi]

Abstract

Abstract is missing.