Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915510306734080 |
|---|---|
| author | Min, Yimeng Gomes, Carla P. |
| author_facet | Min, Yimeng Gomes, Carla P. |
| contents | We propose a non-autoregressive framework for the Travelling Salesman Problem where solutions emerge directly from learned permutations, without requiring explicit search. By applying a similarity transformation to Hamiltonian cycles, the model learns to approximate permutation matrices via continuous relaxations. Our unsupervised approach achieves competitive performance against classical heuristics, demonstrating that the inherent structure of the problem can effectively guide combinatorial optimization without sequential decision-making. Our method offers concrete evidence that neural networks can directly capture and exploit combinatorial structure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04164 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization Min, Yimeng Gomes, Carla P. Machine Learning Artificial Intelligence We propose a non-autoregressive framework for the Travelling Salesman Problem where solutions emerge directly from learned permutations, without requiring explicit search. By applying a similarity transformation to Hamiltonian cycles, the model learns to approximate permutation matrices via continuous relaxations. Our unsupervised approach achieves competitive performance against classical heuristics, demonstrating that the inherent structure of the problem can effectively guide combinatorial optimization without sequential decision-making. Our method offers concrete evidence that neural networks can directly capture and exploit combinatorial structure. |
| title | Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.04164 |