Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
Machine Learning
2020-07-01 v1 Machine Learning
Abstract
This paper presents a framework of successive functional gradient optimization for training nonconvex models such as neural networks, where training is driven by mirror descent in a function space. We provide a theoretical analysis and empirical study of the training method derived from this framework. It is shown that the method leads to better performance than that of standard training techniques.
Cite
@article{arxiv.2006.16840,
title = {Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization},
author = {Rie Johnson and Tong Zhang},
journal= {arXiv preprint arXiv:2006.16840},
year = {2020}
}
Comments
ICML 2020