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

DOI10.1088/1742-5468/AC3A80MaRDI QIDQ5020049zbMATH OpenOpenAlexFDO

Authors Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, 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)

Recommendations

• Phase diagram of stochastic gradient descent in high-dimensional two-layer neural networks
• Mean-field Langevin dynamics and energy landscape of neural networks
• A mean field view of the landscape of two-layer neural networks
• An analytic theory of shallow networks dynamics for hinge loss classification*

Cites work

• A mean field view of the landscape of two-layer neural networks
• scientific article; zbMATH DE number 1273988 (Why is no real title available?)
• scientific article; zbMATH DE number 976341 (Why is no real title available?)
• scientific article; zbMATH DE number 1998878 (Why is no real title available?)
• Mean-field inference methods for neural networks
• New method for studying the dynamics of disordered spin systems without finite-size effects
• Numerical implementation of dynamical mean field theory for disordered systems: application to the Lotka–Volterra model of ecosystems
• Out-of-equilibrium dynamical mean-field equations for the perceptron model
• Symmetric Langevin spin glass dynamics
• The implicit bias of gradient descent on separable data
• Theory of Simple Glasses

Cited in

(10)

• Hybrid deterministic-stochastic gradient Langevin dynamics for Bayesian learning
• An analytic theory of shallow networks dynamics for hinge loss classification*
• Gradient descent dynamics and the jamming transition in infinite dimensions
• Analysis of kinetic models for label switching and stochastic gradient descent
• Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
• On weak ergodicity breaking in mean-field spin glasses
• Phase diagram of stochastic gradient descent in high-dimensional two-layer neural networks
• Uncertainty quantification for iterative algorithms in linear models with application to early stopping
• Stochastic gradient descent in high dimensions for multi-spiked tensor PCA
• Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5020049)