Mean field analysis of deep neural networks
We analyze multilayer neural networks in the asymptotic regime of simultaneously (a) large network sizes and (b) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the multilayer neural network output. The limit procedure is valid for a...
Main Authors: | Sirignano, J, Spiliopoulos, K |
---|---|
Format: | Journal article |
Language: | English |
Published: |
INFORMS
2021
|
Similar Items
-
Mean field analysis of neural networks: a law of large numbers
by: Sirignano, J, et al.
Published: (2020) -
Mean field analysis of neural networks: a central limit theorem
by: Sirignano, J, et al.
Published: (2019) -
DGM: A deep learning algorithm for solving partial differential equations
by: Sirignano, J, et al.
Published: (2018) -
Proximal mean-field for neural network quantization
by: Ajanthan, T, et al.
Published: (2020) -
Asymmetric mean-field neural networks for multiprocessor scheduling /
by: 286373 Hellstrom, Benjamin J., et al.