Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
Koen Helwegen, James Widdicombe, Lukas Geiger, Zechun Liu, Kwang-Ting Cheng, Roeland Nusselder
Abstract
Optimization of Binarized Neural Networks (BNNs) currently relies on real-valued latent weights to accumulate small update steps. In this paper, we argue that these latent weights cannot be treated analogously to weights in real-valued networks. Instead their main role is to provide inertia during training. We interpret current methods in terms of inertia and provide novel insights into the optimization of BNNs. We subsequently introduce the first optimizer specifically designed for BNNs, Binary Optimizer (Bop), and demonstrate its performance on CIFAR-10 and ImageNet. Together, the redefinition of latent weights as inertia and the introduction of Bop enable a better understanding of BNN optimization and open up the way for further improvements in training methodologies for BNNs.
BibTeX
@inproceedings{NEURIPS2019_9ca8c9b0,
author = {Helwegen, Koen and Widdicombe, James and Geiger, Lukas and Liu, Zechun and Cheng, Kwang-Ting and Nusselder, Roeland},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/9ca8c9b0996bbf05ae7753d34667a6fd-Paper.pdf},
volume = {32},
year = {2019}
}