arXiv (Cornell University) · 2019 · 64 citations · 39 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureSystems ArchitectureSoftware ArchitectureArchitecture ExplorationArchitecture SearchSearch Tree Pruning
Automatic methods for Neural Architecture Search (NAS) have been shown to produce state-of-the-art network models. Yet, their main drawback is the computational complexity of the search process. As some primal methods optimized over a discrete search space, thousands of days of GPU were required for convergence. A recent approach is based on constructing a differentiable search space that enables gradient-based optimization, which reduces the search time to a few days. While successful, it still includes some noncontinuous steps, e.g., the pruning of many weak connections at once. In this paper, we propose a differentiable search space that allows the annealing of architecture weights, while gradually pruning inferior operations. In this way, the search converges to a single output network in a continuous manner. Experiments on several vision datasets demonstrate the effectiveness of our method with respect to the search cost and accuracy of the achieved model. Specifically, with $0.2$ GPU search days we achieve an error rate of $1.68\%$ on CIFAR-10.
39
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
Optimization by Simulated Annealing
Scott Kirkpatrick, C. D. Gelatt, M.P. Vecchi · Science · 1983 · 44.6K citations
Squeeze-and-Excitation Networks
Jie Hu, Li Shen, Samuel Albanie et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2019 · 12.5K citations