Pré-Publication, Document De Travail Année : 2025

Latent Guided Sampling for Combinatorial Optimization

Résumé

Combinatorial Optimization problems are widespread in domains such as logistics, manufacturing, and drug discovery, yet their NP-hard nature makes them computationally challenging. Recent Neural Combinatorial Optimization methods leverage deep learning to learn solution strategies, trained via Supervised or Reinforcement Learning (RL). While promising, these approaches often rely on task-specific augmentations, perform poorly on out-of-distribution instances, and lack robust inference mechanisms. Moreover, existing latent space models either require labeled data or rely on pre-trained policies. In this work, we propose LGS-Net, a novel latent space model that conditions on problem instances, and introduce an efficient inference method, Latent Guided Sampling (LGS), based on Markov Chain Monte Carlo and Stochastic Approximation. We show that the iterations of our method form a time-inhomogeneous Markov Chain and provide rigorous theoretical convergence guarantees. Empirical results on benchmark routing tasks show that our method achieves state-of-the-art performance among RL-based approaches.

Fichier principal
Vignette du fichier
main.pdf (809.47 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05088308 , version 1 (28-05-2025)

Licence

Identifiants

  • HAL Id : hal-05088308 , version 1

Citer

Sobihan Surendran, Adeline Fermanian, Sylvain Le Corff. Latent Guided Sampling for Combinatorial Optimization. 2025. ⟨hal-05088308⟩
48 Consultations
112 Téléchargements

Partager

  • More