In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.
@article{arxiv.1807.04162,
title = {TherML: Thermodynamics of Machine Learning},
author = {Alexander A. Alemi and Ian Fischer},
journal= {arXiv preprint arXiv:1807.04162},
year = {2018}
}
Comments
Presented at the ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models