For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency. Towards achieving this goal, we develop a differentiable NAS solution, where the search space includes arbitrary feed-forward network consisting of the predefined number of connections. Benefiting from a proposed ensemble Gumbel-Softmax estimator, our method optimizes both the architecture of a deep network and its parameters in the same round of backward propagation, yielding an end-to-end mechanism of searching network architectures. Extensive experiments on a variety of popular datasets strongly evidence that our method is capable of discovering high-performance architectures, while guaranteeing the requisite efficiency during searching.
@article{arxiv.1905.01786,
title = {Differentiable Architecture Search with Ensemble Gumbel-Softmax},
author = {Jianlong Chang and Xinbang Zhang and Yiwen Guo and Gaofeng Meng and Shiming Xiang and Chunhong Pan},
journal= {arXiv preprint arXiv:1905.01786},
year = {2019}
}