Entropy, concentration, and learning: a statistical mechanics primer
It provides a foundational primer for researchers in AI and machine learning, but is incremental as it synthesizes existing principles without new empirical results.
The paper explores the connections between statistical mechanics and AI training through loss minimization, highlighting the role of exponential families and sample concentration behaviors.
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.