English

TherML: Thermodynamics of Machine Learning

Machine Learning 2018-10-08 v3 Statistical Mechanics Machine Learning

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-23T02:57:50.185Z