MEP-Net: Generating Solutions to Scientific Problems with Limited Knowledge by Maximum Entropy Principle

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Wuyue, Peng, Liangrong, Li, Guojie, Hong, Liu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913595374174208
author Yang, Wuyue
Peng, Liangrong
Li, Guojie
Hong, Liu
author_facet Yang, Wuyue
Peng, Liangrong
Li, Guojie
Hong, Liu
contents Maximum entropy principle (MEP) offers an effective and unbiased approach to inferring unknown probability distributions when faced with incomplete information, while neural networks provide the flexibility to learn complex distributions from data. This paper proposes a novel neural network architecture, the MEP-Net, which combines the MEP with neural networks to generate probability distributions from moment constraints. We also provide a comprehensive overview of the fundamentals of the maximum entropy principle, its mathematical formulations, and a rigorous justification for its applicability for non-equilibrium systems based on the large deviations principle. Through fruitful numerical experiments, we demonstrate that the MEP-Net can be particularly useful in modeling the evolution of probability distributions in biochemical reaction networks and in generating complex distributions from data.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02090
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MEP-Net: Generating Solutions to Scientific Problems with Limited Knowledge by Maximum Entropy Principle
Yang, Wuyue
Peng, Liangrong
Li, Guojie
Hong, Liu
Machine Learning
Data Analysis, Statistics and Probability
Maximum entropy principle (MEP) offers an effective and unbiased approach to inferring unknown probability distributions when faced with incomplete information, while neural networks provide the flexibility to learn complex distributions from data. This paper proposes a novel neural network architecture, the MEP-Net, which combines the MEP with neural networks to generate probability distributions from moment constraints. We also provide a comprehensive overview of the fundamentals of the maximum entropy principle, its mathematical formulations, and a rigorous justification for its applicability for non-equilibrium systems based on the large deviations principle. Through fruitful numerical experiments, we demonstrate that the MEP-Net can be particularly useful in modeling the evolution of probability distributions in biochemical reaction networks and in generating complex distributions from data.
title MEP-Net: Generating Solutions to Scientific Problems with Limited Knowledge by Maximum Entropy Principle
topic Machine Learning
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2412.02090