# TherML: Thermodynamics of Machine Learning

arXiv: https://arxiv.org/abs/1807.04162 · HTML: https://mlsanity.com/paper/1807.04162/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2018.

## Built on by (most cited first, 9 of 9)

- [Thermodynamic AI and the fluctuation frontier](https://mlsanity.com/paper/2302.06584/) (2023)
- [Differentiable Physics: A Position Piece](https://mlsanity.com/paper/2109.07573/) (2021)
- [An Exploration of Learnt Representations of W Jets](https://mlsanity.com/paper/2109.10919/) (2021)
- [SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training](https://mlsanity.com/paper/2505.23489/) (2025)
- [Machine-Learning Compression for Particle Physics Discoveries](https://mlsanity.com/paper/2210.11489/) (2022)
- [First-Passage Approach to Optimizing Perturbations for Improved Training of Machine Learning Models](https://mlsanity.com/paper/2502.04121/) (2025)
- [Rethinking Neural Networks With Benford's Law](https://mlsanity.com/paper/2102.03313/) (2021)
- [The Phenomenology of Machine: A Comprehensive Analysis of the Sentience of the OpenAI-o1 Model Integrating Functionalism, Consciousness Theories, Active Inference, and AI Architectures](https://mlsanity.com/paper/2410.00033/) (2024)
- [Pareto-optimal clustering with the primal deterministic information bottleneck](https://mlsanity.com/paper/2204.02489/) (2022)

## Abstract (arXiv)

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.