no code implementations • 13 Dec 2021 • Martin Hutzenthaler, Arnulf Jentzen, Katharina Pohl, Adrian Riekert, Luca Scarpa
In many numerical simulations stochastic gradient descent (SGD) type optimization methods perform very effectively in the training of deep neural networks (DNNs) but till this day it remains an open problem of research to provide a mathematical convergence analysis which rigorously explains the success of SGD type optimization methods in the training of DNNs.
no code implementations • 10 Dec 2020 • Alexander Menovschikov, Anastasia Molchanova, Luca Scarpa
We propose an extension of the classical variational theory of evolution equations that accounts for dynamics also in possibly non-reflexive and non-separable spaces.
Analysis of PDEs Functional Analysis 35A15, 35D30, 35K67