NeurIPS 2025spotlight0 citations
Neural Entropy
Abstract
We explore the connection between deep learning and information theory through the paradigm of diffusion models. A diffusion model converts noise into structured data by reinstating, imperfectly, information that is erased when data was diffused to noise. This information is stored in a neural network during training. We quantify this information by introducing a measure called \textit{neural entropy}, which is related to the total entropy produced by diffusion. Neural entropy is a function of not just the data distribution, but also the diffusive process itself. Measurements of neural entropy on a few simple image diffusion models reveal that they are extremely efficient at compressing large ensembles of structured data.
Diffusion modelsthermodynamicsinformation theorystatistical mechanics
BibTeX
@inproceedings{
premkumar2025neural,
title={Neural Entropy},
author={Akhil Premkumar},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=f6AYwCvynr}
}