collaborators

5 papers

cs.LG2025

LLMs for Cold-Start Cutting Plane Separator Configuration

Connor Lawless, Yingxi Li, Anders Wikum +2

Mixed integer linear programming (MILP) solvers expose hundreds of parameters that have an outsized impact on performance but are difficult to configure for all but expert users. E…

cs.HC2025

"It Was a Magical Box": Understanding Practitioner Workflows and Needs in Optimization

Connor Lawless, Jakob Schoeffer, Madeleine Udell

Optimization underpins decision-making in domains from healthcare to logistics, yet for many practitioners it remains a "magical box": powerful but opaque, difficult to use, and re…

cs.LG2025

Understanding Fixed Predictions via Confined Regions

Connor Lawless, Tsui-Wei Weng, Berk Ustun +1

Machine learning models can assign fixed predictions that preclude individuals from changing their outcome. Existing approaches to audit fixed predictions do so on a pointwise basi…

cs.AI2025

EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations

Haotian Zhai, Connor Lawless, Ellen Vitercik +1

A fundamental problem in combinatorial optimization is identifying equivalent formulations. Despite the growing need for automated equivalence checks -- driven, for example, by opt…

cs.HC2024

"I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming

Connor Lawless, Jakob Schoeffer, Lindy Le +5

A critical factor in the success of decision support systems is the accurate modeling of user preferences. Psychology research has demonstrated that users often develop their prefe…