The Decentralized Trust-Region Method with Second-Order Approximations

This paper presents a novel decentralized trust-region framework that systematically incorporates second-order information to solve general nonlinear optimization problems in multi-agent networks. Our approach constructs local quadratic models that simultaneously capture objective curvature and enforce consensus through penalty terms, while supporting multiple Hessian approximation strategies including exact Hessians, limited-memory quasi-Newton methods, diagonal preconditioners, and matrix-free … Read more

Distributed Projections onto a Simplex

Projecting a vector onto a simplex is a well-studied problem that arises in a wide range of optimization problems. Numerous algorithms have been proposed for determining the projection; however, all but one of these algorithms are serial. We address this gap by developing a method that preprocesses the input vector by decomposing and distributing it … Read more

A Class of Randomized Primal-Dual Algorithms for Distributed Optimization

Based on a preconditioned version of the randomized block-coordinate forward-backward algorithm recently proposed in [Combettes,Pesquet,2014], several variants of block-coordinate primal-dual algorithms are designed in order to solve a wide array of monotone inclusion problems. These methods rely on a sweep of blocks of variables which are activated at each iteration according to a random rule, … Read more