In this talk we apply the Parallel Coordinate Descent for SVM dual and compare it with stochastic subgradient descent (SGD) approach. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup for both algorithms. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss.
Current 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 2009 2008 2007 2006 2005 2004 2003 2002 2001 2000 1999 1998 1997 1996
