Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems
Machine Learning
2025-11-05 v1
Abstract
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 value of instances from the underlying distribution of objectives and their respective sub-instances. The training of the estimator is based on an inequality that facilitates the use of the expected total deviation from optimality conditions as a loss function rather than the objective-function itself. Thus, it does not calculate values of policies, nor does it rely on solved instances.
Cite
@article{arxiv.2511.02048,
title = {Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems},
author = {Nimrod Megiddo and Segev Wasserkrug and Orit Davidovich and Shimrit Shtern},
journal= {arXiv preprint arXiv:2511.02048},
year = {2025}
}