Probabilistic programs are widely used decision models. When implemented in practice, however, there often exists distributional ambiguity in these models. In this paper, we model the ambiguity using the likelihood ratio (LR) and use LR to construct various ambiguity sets. We consider ambiguous probabilistic programs which optimize under the worst case. Ambiguous probabilistic programs can … Read more
We introduce a proximal version of the stochastic dual coordinate ascent method and show how to accelerate the method using an inner-outer iteration procedure. We analyze the runtime of the framework and obtain rates that improve state-of-the-art results for various key machine learning optimization problems including SVM, logistic regression, ridge regression, Lasso, and multiclass SVM. … Read more
We establish that the extension complexity of the nXn correlation polytope is at least 1.5^n by a short proof that is self-contained except for using the fact that every face of a polyhedron is the intersection of all facets it is contained in. The main innovative aspect of the proof is a simple combinatorial argument … Read more
The primal-dual column generation method (PDCGM) is a general-purpose column generation technique that relies on the primal-dual interior point method to solve the restricted master problems. The use of this interior point method variant allows to obtain suboptimal and well-centered dual solutions which naturally stabilizes the column generation. A reduction in the number of calls … Read more
A popular discrete choice model that incorporates correlation information is the Multinomial Probit (MNP) model where the random utilities of the alternatives are chosen from a multivariate normal distribution. Computing the choice probabilities is challenging in the MNP model when the number of alternatives is large and simulation is used to approximate the choice probabilities. … Read more
We study a Newton-like method for the minimization of an objective function $\phi$ that is the sum of a smooth convex function and an $\ell_1$ regularization term. This method, which is sometimes referred to in the literature as a proximal Newton method, computes a step by minimizing a piecewise quadratic model $q_k$ of the objective … Read more
In this paper, we present a new stochastic algorithm, namely the stochastic block mirror descent (SBMD) method for solving large-scale nonsmooth and stochastic optimization problems. The basic idea of this algorithm is to incorporate the block-coordinate decomposition and an incremental block averaging scheme into the classic (stochastic) mirror-descent method, in order to significantly reduce the … Read more
We show that quadratic growth of a semi-algebraic function is equivalent to strong metric subregularity of the subdifferential — a kind of stability of generalized critical points. In contrast, this equivalence can easily fail outside of the semi-algebraic setting. Citation 13 pages, September, 2013 Article Download View Quadratic growth and critical point stability of semi-algebraic … Read more
We are interested in optimizing the co-administration of two drugs for some acute myeloid leukemias (AML), and we are looking for in vitro protocols as a first step. This issue can be formulated as an optimal control problem. The dynamics of leukemic cell populations in culture is given by age-structured partial differential equations, which can … Read more
This paper focuses on solving two-stage stochastic mixed integer programs (SMIPs) with general mixed integer decision variables in both stages. We develop a decomposition algorithm in which the first stage approximation is solved using a branch-and-bound tree with nodes inheriting Benders’ cuts that are valid for their ancestor nodes. In addition, we develop two closely … Read more