collaborators

13 papers

math.OC2026

Lipschitzian SLLNs for random functions

Lai Tian, Johannes O. Royset

We prove strong laws of large numbers for locally Lipschitz functions in the Lipschitz pseudometric. Our results hold under either a topological or a model-theoretic condition, wit…

math.OC2026

Perturbation Duality for Robust and Distributionally Robust Optimization: Short and General Proofs

Louis L. Chen, Jake Roth, Johannes O. Royset

Duality is a foundational tool in robust and distributionally robust optimization (RO/DRO), underpinning both analytical insights and tractable reformulations. Whereas RO/DRO duali…

math.OC2026

Failure of uniform laws of large numbers for subdifferentials and beyond

Lai Tian, Johannes O. Royset

We provide counterexamples showing that uniform laws of large numbers do not hold for subdifferentials under natural assumptions. Our constructions are univariate random Lipschitz…

math.OC2026

Composite Optimization using Local Models and Global Approximations

Welington de Oliveira, Johannes O. Royset

This work presents a unified framework that combines global approximations with locally built models to handle challenging nonconvex and nonsmooth composite optimization problems,…

math.OC2026

Optimistic Bilevel Optimization with Composite Lower-Level Problem

Mattia Solla, Johannes O. Royset

This paper introduces a novel double regularization scheme for bilevel optimization problems whose lower-level problem is composite and convex, but not necessarily strongly convex,…

cs.LG2026

Membership Privacy Risks of Sharpness Aware Minimization

Young In Kim, Andrea Agiollo, Pratiksha Agrawal +2

Optimization algorithms that seek flatter minima, such as Sharpness-Aware Minimization (SAM), are credited with improved generalization and robustness to noise. We ask whether such…