Quoc Tran-DinhAnastasios KyrillidisVolkan CevherA proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions.271-2792013ICML (2)http://proceedings.mlr.press/v28/trandinh13.htmlconf/icml/2013db/conf/icml/icml2013.html#Tran-DinhKC13