This article presents a powerful algorithmic framework for big data optimization, called the
block successive upper-bound minimization (BSUM). The BSUM includes as special cases …

We study optimization algorithms based on variance reduction for stochastic
gradientdescent (SGD). Remarkable recent progress has been made in this …

In this paper we develop random block coordinate descent methods for minimizing large-
scale linearly constrained convex problems over networks. Since coupled constraints …

We propose an accelerated stochastic block coordinate descent algorithm for nonconvex
optimization under sparsity constraint in the high dimensional regime. The core of our …

We study the composite minimization problem where the objective function is the sum of two
convex functions: one is the sum of a finite number of strongly convex and smooth functions …

We consider the minimization of a convex function over a bounded polyhedral constraint set
where the number of vertices of the polyhedron is not too large such as the-ball and the …

Prediction markets are economic mechanisms for aggregating information about future
events through sequential interactions with traders. The pricing mechanisms in these …

A block decomposition method is proposed for minimizing a (possibly non-convex)
continuously differentiable function subject to one linear equality constraint and simple …

In this paper we consider large-scale smooth optimization problems with multiple linear
coupled constraints. Due to the non-separability of the constraints, arbitrary random …

Abstract Graph Semi-Supervised learning is an important data analysis tool, where given a
graph and a set of labeled nodes, the aim is to infer the labels to the remaining unlabeled …