A Unified Framework for Training Neural Networks
Abstract
The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for training different types of DNNs, and establish its convergence for arbitrary loss, activation, and regularization functions, assumed to be smooth. We show that framework generalizes well-known first- and second-order training methods, and thus allows us to show the convergence of these methods for various DNN architectures and learning tasks, as a special case of our approach. We discuss some of its applications in training various DNN architectures (e.g., feed-forward, convolutional, linear networks), to regression and classification tasks.
Cite
@article{arxiv.1805.09214,
title = {A Unified Framework for Training Neural Networks},
author = {Hadi Ghauch and Hossein Shokri-Ghadikolaei and Carlo Fischione and Mikael Skoglund},
journal= {arXiv preprint arXiv:1805.09214},
year = {2018}
}
Comments
15 pages, submitted to NIPS 2018