Efficient QUIC-Based Damped Inexact Iterative Reweighting for Sparse Inverse Covariance Estimation with Nonconvex Partly Smooth Regularization

In this paper, we study sparse inverse covariance matrix estimation incorporating partly smooth nonconvex regularizers. To solve the resulting regularized log-determinant problem, we develop DIIR-QUIC—a novel Damped Inexact Iteratively Reweighted algorithm based on QUadratic approximate Inverse Covariance (QUIC) method. Our approach generalizes the classic iteratively reweighted \(\ell_1\) scheme through damped fixed-point updates. A key novelty … Read more

Dual certificates of primal cone membership

We discuss easily verifiable cone membership certificates, that is, certificates proving relations of the form \( b\in K \) for convex cones \(K\) that consist of vectors in the dual cone \(K^*\). Vectors in the dual cone are usually associated with separating hyperplanes, and so they are interpreted as certificates of non-membership in the standard … Read more

Asymptotically Fair and Truthful Allocation of Public Goods

We study the fair and truthful allocation of m divisible public items among n agents, each with distinct preferences for the items. To aggregate agents’ preferences fairly, we focus on finding a core solution. For divisible items, a core solution always exists and can be calculated by maximizing the Nash welfare objective. However, such a … Read more

Lipschitz-Free Mirror Descent Methods for Non-Smooth Optimization Problems

The part of the analysis of the convergence rate of the mirror descent method that is connected with the adaptive time-varying step size rules due to Alkousa et al. (MOTOR 2024, pp. 3-18) is corrected. Moreover, a Lipschitz-free mirror descent method that achieves weak ergodic convergence is presented, generalizing the convergence results of the mirror … Read more

Gradient Methods with Online Scaling Part I. Theoretical Foundations

This paper establishes the theoretical foundations of the online scaled gradient methods (OSGM), a framework that utilizes online learning to adapt stepsizes and provably accelerate first-order methods. OSGM quantifies the effectiveness of a stepsize by a feedback function motivated from a convergence measure and uses the feedback to adjust the stepsize through an online learning … Read more

A symmetric extrapolated proximal alternating predictor-corrector method for saddle-point problems

The proximal alternating predictor-corrector (PAPC) method is a widely used first-order algorithm for solving convex-concave saddle-point problems involving both smooth and nonsmooth components. Unlike the primal-dual hybrid gradient (PDHG) method, which incorporates an extrapolation step with parameter $\theta \in (0,1]$ to improve convergence, the existing convergence analysis of PAPC has been limited to the case … Read more

Multi-cut stochastic approximation methods for solving stochastic convex composite optimization

The development of a multi-cut stochastic approximation (SA) method for solving stochastic convex composite optimization (SCCO) problems has remained an open challenge. The difficulty arises from the fact that the stochastic multi-cut model, constructed as the pointwise maximum of individual stochastic linearizations, provides a biased estimate of the objective function, with the error being uncontrollable. … Read more

Inverse Optimization via Learning Feasible Regions

We study inverse optimization (IO), where the goal is to use a parametric optimization program as the hypothesis class to infer relationships between input-decision pairs. Most of the literature focuses on learning only the objective function, as learning the constraint function (i.e., feasible regions) leads to nonconvex training programs. Motivated by this, we focus on … Read more

cuHALLaR: A GPU accelerated low-rank augmented Lagrangian method for large-scale semidefinite programming

This paper introduces cuHALLaR, a GPU-accelerated implementation of the HALLaR method proposed in Monteiro et al. 2024 for solving large-scale semidefinite programming (SDP) problems. We demonstrate how our Julia-based implementation efficiently uses GPU parallelism through optimization of simple, but key, operations, including linear maps, adjoints, and gradient evaluations. Extensive numerical experiments across three problem classes—maximum … Read more

Subgradient Regularization: A Descent-Oriented Subgradient Method for Nonsmooth Optimization

In nonsmooth optimization, a negative subgradient is not necessarily a descent direction, making the design of convergent descent methods based on zeroth-order and first-order information a challenging task. The well-studied bundle methods and gradient sampling algorithms construct descent directions by aggregating subgradients at nearby points in seemingly different ways, and are often complicated or lack … Read more