Neural Network Architecture Optimization through Submodularity and Supermodularity
Abstract
Deep learning models' architectures, including depth and width, are key factors influencing models' performance, such as test accuracy and computation time. This paper solves two problems: given computation time budget, choose an architecture to maximize accuracy, and given accuracy requirement, choose an architecture to minimize computation time. We convert this architecture optimization into a subset selection problem. With accuracy's submodularity and computation time's supermodularity, we propose efficient greedy optimization algorithms. The experiments demonstrate our algorithm's ability to find more accurate models or faster models. By analyzing architecture evolution with growing time budget, we discuss relationships among accuracy, time and architecture, and give suggestions on neural network architecture design.
Cite
@article{arxiv.1609.00074,
title = {Neural Network Architecture Optimization through Submodularity and Supermodularity},
author = {Junqi Jin and Ziang Yan and Kun Fu and Nan Jiang and Changshui Zhang},
journal= {arXiv preprint arXiv:1609.00074},
year = {2018}
}
Comments
Withdrawn due to incompleteness and some overlaps with existing literatures, I will resubmit adding further results