Entropy, concentration, and learning: a statistical mechanics primer
Machine Learning
2024-09-30 v1 Statistical Mechanics
Artificial Intelligence
Information Theory
math.IT
Machine Learning
Abstract
Artificial intelligence models trained through loss minimization have demonstrated significant success, grounded in principles from fields like information theory and statistical physics. This work explores these established connections through the lens of statistical mechanics, starting from first-principles sample concentration behaviors that underpin AI and machine learning. Our development of statistical mechanics for modeling highlights the key role of exponential families, and quantities of statistics, physics, and information theory.
Cite
@article{arxiv.2409.18630,
title = {Entropy, concentration, and learning: a statistical mechanics primer},
author = {Akshay Balsubramani},
journal= {arXiv preprint arXiv:2409.18630},
year = {2024}
}