We propose a simple proof of the worst-case iteration complexity for the Difference of Convex functions Algorithm (DCA) for unconstrained minimization, showing that the global rate of convergence of the norm of the objective function’s gradients at the iterates converge to zero like $o(1/k)$. A small example is also provided indicating that the rate cannot … Read more
This paper investigates non-convex stochastic compositional optimization under heavy-tailed noise, where the stochastic noise exhibits bounded $p$th moment with $p\in(1,2]$. The main challenges arise from biased gradient estimates of the objective and the violation of the standard bounded-variance assumption. To address these issues, we propose a generic algorithm framework of Normalized Stochastic Compositional Gradient methods … Read more
We generalize tilt stability, a fundamental concept in perturbation analysis of optimization problems in Euclidean spaces, to the setting of Riemannian manifolds. We prove the equivalence of the following conditions: Riemannian tilt stability, Riemannian variational strong convexity, Riemannian uniform quadratic growth, local strong monotonicity of Riemannian subdifferential, strong metric regularity of Riemannian subdifferential, and positive … Read more
This paper proposes an improved quasi-Newton penalty decomposition algorithm for the minimization of continuously differentiable functions, possibly nonconvex, over sparse symmetric sets. The method solves a sequence of penalty subproblems approximately via a two-block decomposition scheme: the first subproblem admits a closed-form solution without sparsity constraints, while the second subproblem is handled through an efficient … Read more
Two algorithms are proposed, analyzed, and tested for solving continuous optimization problems with nonlinear equality constraints. Each is an extension of a stochastic momentum-based method from the unconstrained setting to the setting of a stochastic Newton-SQP-type algorithm for solving equality-constrained problems. One is an extension of the heavy-ball method and the other is an extension … Read more
In this paper, we introduce a framework for contextual distributionally robust optimization (DRO) that considers the causal and continuous structure of the underlying distribution by developing interpretable and tractable decision rules that prescribe decisions using covariates. We first introduce the causal Sinkhorn discrepancy (CSD), an entropy-regularized causal Wasserstein distance that encourages continuous transport plans while … Read more
ArticleDownload View PDF
In this work, we study a recent extension to the well-known Steiner tree problem: the Generalized Group Steiner Tree problem with logical side constraints. In this variant, we aim to identify a tree of minimum total cost, that spans a given set of groups of nodes, like in the traditional Group Steiner Tree problem. However, … Read more
We consider a quadratic minmax problem with coupled inner constraints and propose a method to compute a class of stationary points. To motivate the need to compute such stationary points, we first show that they are meaningful, in the sense that they can be locally optimal for our problem under suitable linear independence and second-order … Read more
In this paper, we develop a unified majorization-minimization scheme and convergence analysis with first-order surrogate functions for unconstrained vector optimization problems (VOPs). By selecting different surrogate functions, the unified method can be reduced to various existing first-order methods. The unified convergence analysis reveals that the slow convergence of the steepest descent method is primarily attributed … Read more