collaborators

5 papers

cs.AI2026

An Agent-Based Framework for the Automatic Validation of Mathematical Optimization Models

Alexander Zadorojniy, Segev Wasserkrug, Eitan Farchi

Recently, using Large Language Models (LLMs) to generate optimization models from natural language descriptions has became increasingly popular. However, a major open question is h…

stat.ML2026

Heuristics for Combinatorial Optimization via Value-based Reinforcement Learning: A Unified Framework and Analysis

Orit Davidovich, Shimrit Shtern, Segev Wasserkrug +1

Since the 1990s, considerable empirical work has been carried out to train statistical models, such as neural networks (NNs), as learned heuristics for combinatorial optimization (…

cs.LG2025

Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems

Nimrod Megiddo, Segev Wasserkrug, Orit Davidovich +1

The paper is about developing a solver for maximizing a real-valued function of binary variables. The solver relies on an algorithm that estimates the optimal objective-function va…

cs.CY2025

Making a Case for Research Collaboration Between Artificial Intelligence and Operations Research Experts

Radhika Kulkarni, Gianluca Brero, Yu Ding +7

In 2021, INFORMS, ACM SIGAI, and the Computing Community Consortium (CCC) hosted three workshops to explore synergies between Artificial Intelligence (AI) and Operations Research (…

cs.GT2025

Achieving PAC Guarantees in Mechanism Design through Multi-Armed Bandits

Takayuki Osogami, Hirota Kinoshita, Segev Wasserkrug

We analytically derive a class of optimal solutions to a linear program (LP) for automated mechanism design that satisfies efficiency, incentive compatibility, strong budget balanc…