Efficient Methods for Stochastic Composite Optimization

This paper considers an important class of convex programming problems whose objective function $\Psi$ is given by the summation of a smooth and non-smooth component. Further, it is assumed that the only information available for the numerical scheme to solve these problems is the subgradient of $\Psi$ contaminated by stochastic noise. Our contribution mainly consists … Read more

Iteration-complexity of first-order penalty methods

This paper considers a special but broad class of convex programing (CP) problems whose feasible region is a simple compact convex set intersected with the inverse image of a closed convex cone under an affine transformation. We study two first-order penalty methods for solving the above class of problems, namely: the quadratic penalty method and … Read more

Validation Analysis of Robust Stochastic Approximation Method

The main goal of this paper is to develop accuracy estimates for stochastic programming problems by employing robust stochastic approximation (SA) type algorithms. To this end we show that while running a Robust Mirror Descent Stochastic Approximation procedure one can compute, with a small additional effort, lower and upper statistical bounds for the optimal objective … Read more

Stochastic Approximation approach to Stochastic Programming

In this paper we consider optimization problems where the objective function is given in a form of the expectation. A basic difficulty of solving such stochastic optimization problems is that the involved multidimensional integrals (expectations) cannot be computed with high accuracy. The aim of this paper is to compare two computational approaches based on Monte … Read more

A polynomial predictor-corrector trust-region algorithm for linear programming

In this paper we present a scaling-invariant interior-point predictor-corrector type algorithm for linear programming (LP) whose iteration-complexity is polynomially bounded by the dimension and the logarithm of a certain condition number of the LP constraint matrix. At the predictor stage, the algorithm either takes the step along the standard affine scaling direction or a new … Read more

Primal-dual first-order methods with ${\cal O}(1/\epsilon)$ iteration-complexity for cone programming

In this paper we consider the general cone programming problem, and propose primal-dual convex (smooth and/or nonsmooth) minimization reformulations for it. We then discuss first-order methods suitable for solving these reformulations, namely, Nesterov’s optimal method \cite{Nest83-1,Nest05-1}, Nesterov’s smooth approximation scheme \cite{Nest05-1}, and Nemirovski’s prox-method \cite{Nem05-1}, and propose a variant of Nesterov’s optimal method which has … Read more