Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Thyssens, Daniela, Dernedde, Tim, Sentanoe, Wilson, Schmidt-Thieme, Lars
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.02510
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908477952098304
author Thyssens, Daniela
Dernedde, Tim
Sentanoe, Wilson
Schmidt-Thieme, Lars
author_facet Thyssens, Daniela
Dernedde, Tim
Sentanoe, Wilson
Schmidt-Thieme, Lars
contents Neural Combinatorial Optimization aims to learn to solve a class of combinatorial problems through data-driven methods and notably through employing neural networks by learning the underlying distribution of problem instances. While, so far neural methods struggle to outperform highly engineered problem specific meta-heuristics, this work explores a novel approach to formulate the distribution of problem instances to learn from and, more importantly, plant a structure in the sampled problem instances. In application to routing problems, we generate large problem instances that represent custom base problem instance distributions from which training instances are sampled. The test instances to evaluate the methods on the routing task consist of unseen problems sampled from the underlying large problem instance. We evaluate representative NCO methods and specialized Operation Research meta heuristics on this novel task and demonstrate that the performance gap between neural routing solvers and highly specialized meta-heuristics decreases when learning from sub-samples drawn from a fixed base node distribution.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02510
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Distributional Dependent Performance of Classical and Neural Routing Solvers
Thyssens, Daniela
Dernedde, Tim
Sentanoe, Wilson
Schmidt-Thieme, Lars
Machine Learning
Neural Combinatorial Optimization aims to learn to solve a class of combinatorial problems through data-driven methods and notably through employing neural networks by learning the underlying distribution of problem instances. While, so far neural methods struggle to outperform highly engineered problem specific meta-heuristics, this work explores a novel approach to formulate the distribution of problem instances to learn from and, more importantly, plant a structure in the sampled problem instances. In application to routing problems, we generate large problem instances that represent custom base problem instance distributions from which training instances are sampled. The test instances to evaluate the methods on the routing task consist of unseen problems sampled from the underlying large problem instance. We evaluate representative NCO methods and specialized Operation Research meta heuristics on this novel task and demonstrate that the performance gap between neural routing solvers and highly specialized meta-heuristics decreases when learning from sub-samples drawn from a fixed base node distribution.
title On Distributional Dependent Performance of Classical and Neural Routing Solvers
topic Machine Learning
url https://arxiv.org/abs/2508.02510