Papers › Fast and Functional Structured Data Generators Rooted in Out-of-Equilibrium Physics

Fast and Functional Structured Data Generators Rooted in Out-of-Equilibrium Physics

13 Jul 2023arXiv:2307.06797archive 2025-07-28

Alessandra Carbone, Aurélien Decelle, Lorenzo Rosset, Beatriz Seoane

In this study, we address the challenge of using energy-based models to produce high-quality, label-specific data in complex structured datasets, such as population genetics, RNA or protein sequences data. Traditional training methods encounter difficulties due to inefficient Markov chain Monte Carlo mixing, which affects the diversity of synthetic data and increases generation times. To address these issues, we use a novel training algorithm that exploits non-equilibrium effects. This approach, applied on the Restricted Boltzmann Machine, improves the model's ability to correctly classify samples and generate high-quality synthetic data in only a few sampling steps. The effectiveness of this method is demonstrated by its successful application to four different types of data: handwritten digits, mutations of human genomes classified by continental origin, functionally characterized sequences of an enzyme protein family, and homologous RNA sequences from specific taxonomies.

PaperPDFCode

Code

dsysdml/fef officialmentioned in papermentioned on GitHubpytorch report
rossetl/fef officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Diversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Restricted Boltzmann Machine

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections