Yuchen Zhang – Optimization Online

Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss

Published: 2015/01/05

Convex Optimization, Statistics distributed optimization, empirical risk minimization, inexact newton method, preconditioned conjugate gradient, self-concordance

We consider distributed convex optimization problems originated from sample average approximation of stochastic optimization, or empirical risk minimization in machine learning. We assume that each machine in the distributed computing system has access to a local empirical loss function, constructed with i.i.d. data sampled from a common distribution. We propose a communication-efficient distributed algorithm to … Read more

Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization

Published: 2014/09/12

Lin Xiao

Yuchen Zhang

Convex and Nonsmooth Optimization accelerated primal-dual algorithms, empirical risk minimization, stochastic coordinate descent/ascent method

We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors. The problem structure allows us to reformulate it as a convex-concave saddle point problem. We propose a stochastic primal-dual coordinate (SPDC) method, which alternates between maximizing over a randomly chosen dual variable and minimizing over the primal variable. An … Read more