3 papers
cs.LG2025
Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization
Yimeng Min, Carla P. Gomes
We propose a non-autoregressive framework for the Travelling Salesman Problem where solutions emerge directly from learned permutations, without requiring explicit search. By apply…
cs.LG2025
Unsupervised Ordering for Maximum Clique
Yimeng Min, Carla P. Gomes
We propose an unsupervised approach for learning vertex orderings for the maximum clique problem by framing it within a permutation-based framework. We transform the combinatorial…
cs.AI2024
On Size and Hardness Generalization in Unsupervised Learning for the Travelling Salesman Problem
Yimeng Min, Carla P. Gomes
We study the generalization capability of Unsupervised Learning in solving the Travelling Salesman Problem (TSP). We use a Graph Neural Network (GNN) trained with a surrogate loss…