Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
| Autor: | Simone Ciarella, Jeanne Trinquier, Martin Weigt, Francesco Zamponi |
|---|---|
| Přispěvatelé: | Systèmes Désordonnés et Applications, Laboratoire de physique de l'ENS - ENS Paris (LPENS), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)-Département de Physique de l'ENS-PSL, École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)-Département de Physique de l'ENS-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Biologie Computationnelle et Quantitative = Laboratory of Computational and Quantitative Biology (LCQB), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut de Biologie Paris Seine (IBPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), European Project: 723955,GlassUniversality |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
Human-Computer Interaction
Artificial Intelligence FOS: Physical sciences [PHYS.COND.CM-DS-NN]Physics [physics]/Condensed Matter [cond-mat]/Disordered Systems and Neural Networks [cond-mat.dis-nn] Disordered Systems and Neural Networks (cond-mat.dis-nn) Condensed Matter - Disordered Systems and Neural Networks Software |
| Zdroj: | Machine Learning: Science and Technology Machine Learning: Science and Technology, 2023, 4 (1), pp.010501. ⟨10.1088/2632-2153/acbe91⟩ |
| ISSN: | 2632-2153 |
| Popis: | Several strategies have been recently proposed in order to improve Monte Carlo sampling efficiency using machine learning tools. Here, we challenge these methods by considering a class of problems that are known to be exponentially hard to sample using conventional local Monte Carlo at low enough temperatures. In particular, we study the antiferromagnetic Potts model on a random graph, which reduces to the coloring of random graphs at zero temperature. We test several machine-learning-assisted Monte Carlo approaches, and we find that they all fail. Our work thus provides good benchmarks for future proposals for smart sampling algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|