English

Differentiable Architecture Search with Ensemble Gumbel-Softmax

Machine Learning 2019-05-07 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T08:57:36.692Z