SDNA: Stochastic Dual Newton Ascent for Empirical Risk MinimizationDownload PDFOpen Website

2016 (modified: 11 Nov 2022)ICML 2016Readers: Everyone
Abstract: We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subset of the dual var...
0 Replies

Loading