Machine learning at the mesoscale: a computation-dissipation bottleneck
Statistical Mechanics
2023-07-06 v1 Disordered Systems and Neural Networks
Machine Learning
Abstract
The cost of information processing in physical systems calls for a trade-off between performance and energetic expenditure. Here we formulate and study a computation-dissipation bottleneck in mesoscopic systems used as input-output devices. Using both real datasets and synthetic tasks, we show how non-equilibrium leads to enhanced performance. Our framework sheds light on a crucial compromise between information compression, input-output computation and dynamic irreversibility induced by non-reciprocal interactions.
Cite
@article{arxiv.2307.02379,
title = {Machine learning at the mesoscale: a computation-dissipation bottleneck},
author = {Alessandro Ingrosso and Emanuele Panizon},
journal= {arXiv preprint arXiv:2307.02379},
year = {2023}
}
Comments
12 pages, 5 figures