Closed dynamical mean field equations describe train and test loss trajectories of randomly initialized deep linear networks at large width and data, capturing hyperparameter transfer and power-law scaling.
Out-of-equilibrium dynamical mean-field equations for the perceptron model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
Closed dynamical mean field equations describe train and test loss trajectories of randomly initialized deep linear networks at large width and data, capturing hyperparameter transfer and power-law scaling.