collaborators

9 papers

math.OC2026

Diffusion-Robust Optimization over Graphs

Liviu Aolaritei, Ricky Huang, Michael I. Jordan +1

We introduce a diffusion-based uncertainty model for robust optimization on directed graphs, in which perturbations of edge weights propagate along adjacent edges and satisfy conse…

cs.LG2026

Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback

Wyame Benslimane, Tinghan Ye, Pascal Van Hentenryck +1

Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy. For contextual linear optimization, m…

math.OC2026

A Barrier-Metric First-Order Method for Linearly Constrained Bilevel Optimization

Tenglong Hong, Paul Grigas

We study bilevel optimization with a fixed polyhedral lower feasible set. Such problems are challenging for two reasons: active-set changes can make the upper objective nonsmooth,…

math.OC2026

Direct Spectral Acceleration of First-Order Methods for Saddle Point Problems with Bilinear Coupling

Meng Li, Paul Grigas

We study convex-concave saddle point problems with bilinear coupling, covering linearly constrained convex optimization and more general nonsmooth or constrained models via a proxi…

stat.ML2026

Decision-Focused Sequential Experimental Design: A Directional Uncertainty-Guided Approach

Beichen Wan, Mo Liu, Paul Grigas +1

We consider the sequential experimental design problem in the predict-then-optimize paradigm. In this paradigm, the outputs of the prediction model are used as coefficient vectors…

cs.LG2025

Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints

Hyungki Im, Wyame Benslimane, Paul Grigas

We study an extension of contextual stochastic linear optimization (CSLO) that, in contrast to most of the existing literature, involves inequality constraints that depend on uncer…