Training Deep Neural Networks via Branch-and-Bound
Abstract
In this paper, we propose BPGrad, a novel approximate algorithm for deep nueral network training, based on adaptive estimates of feasible region via branch-and-bound. The method is based on the assumption of Lipschitz continuity in objective function, and as a result, it can adaptively determine the step size for the current gradient given the history of previous updates. We prove that, by repeating such a branch-and-pruning procedure, it can achieve the optimal solution within finite iterations. A computationally efficient solver based on BPGrad has been proposed to train the deep neural networks. Empirical results demonstrate that BPGrad solver works well in practice and compares favorably to other stochastic optimization methods in the tasks of object recognition, detection, and segmentation. The code is available at \url{https://github.com/RyanCV/BPGrad}.
Cite
@article{arxiv.2104.01730,
title = {Training Deep Neural Networks via Branch-and-Bound},
author = {Yuanwei Wu and Ziming Zhang and Guanghui Wang},
journal= {arXiv preprint arXiv:2104.01730},
year = {2021}
}
Comments
29 pages, 17 figures. arXiv admin note: substantial text overlap with arXiv:1711.06959