statistical mechanics
PulseAugur coverage of statistical mechanics — every cluster mentioning statistical mechanics across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New framework details thermodynamics of learning in finite devices
Researchers have introduced a new framework for understanding learning in finite devices, distinguishing between what a device has recorded and what will hold future value. This framework separates learning into four co…
-
Neural network generalization near interpolation analyzed via statistical mechanics · 2 sources tracked
Two new arXiv papers explore the behavior of shallow neural networks with extensive width, focusing on their generalization capabilities near the interpolation threshold. The research analyzes these networks using stati…
-
Hopfield Model from Spin Glasses Offers New AI Teaching Path
A new paper published on arXiv explores the Hopfield model, a concept originating from spin glasses, as a pedagogical tool for teaching artificial intelligence and statistical mechanics. The authors, including Mauricio …
-
New research explores Gaussian Mixture Models via spherical decomposition and statistical mechanics
Two new research papers explore Gaussian Mixture Models (GMMs) from different analytical perspectives. The first paper introduces a method using spherical radial decomposition to represent GMM probability functions as i…
-
Statistical mechanics used to explain machine learning and memorization
This thesis explores the theoretical underpinnings of machine learning and artificial neural networks using tools from statistical mechanics. It aims to improve understanding of how these systems learn and memorize data…
-
New research frames generative models via stochastic thermodynamics
A new paper explores the application of stochastic thermodynamics to SDE-based generative models, such as diffusion models and the Schrödinger bridge. The research introduces trajectory-level definitions for work, heat,…
-
New complexity analysis for normalizing constant estimation in ML
Researchers have developed a new theoretical framework for analyzing the complexity of estimating normalizing constants in probability distributions. This work focuses on annealed importance sampling methods, providing …