Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification*

DOI10.1088/1742-5468/ac3a80OpenAlexW3102766317MaRDI QIDQ5020049

Pierfrancesco Urbani, Francesca Mignacco, Florent Krzakala, Lenka Zdeborová

Publication date: 3 January 2022

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.06098

zbMATH Keywords

learning theorymachine learning

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items (1)

Gradient descent dynamics and the jamming transition in infinite dimensions

Cites Work

• Symmetric Langevin spin glass dynamics
• New method for studying the dynamics of disordered spin systems without finite-size effects
• A mean field view of the landscape of two-layer neural networks
• Mean-field inference methods for neural networks
• Theory of Simple Glasses
• Out-of-equilibrium dynamical mean-field equations for the perceptron model
• Numerical implementation of dynamical mean field theory for disordered systems: application to the Lotka–Volterra model of ecosystems
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification*