Neural Architecture Search via Combinatorial Multi-Armed Bandit

Abstract

Neural Architecture Search (NAS) has gained significant popularity as an effective tool for designing high performance deep neural networks (DNNs). NAS can be performed via policy gradient, evolutionary algorithms, differentiable architecture search or tree-search methods. While significant progress has been made for both policy gradient and differentiable architecture search, tree-search methods have so far failed to achieve comparable accuracy or search efficiency. In this paper, we formulate NAS as a Combinatorial Multi-Armed Bandit (CMAB) problem (CMAB-NAS). This allows the decomposition of a large search space into smaller blocks where tree-search methods can be applied more effectively and efficiently. We further leverage a tree-based method called Nested Monte-Carlo Search to tackle the CMAB-NAS problem. On CIFAR-10, our approach discovers a cell structure that achieves a low error rate that is comparable to the state-of-the-art, using only 0.58 GPU days, which is 20 times faster than current tree-search methods. Moreover, the discovered structure transfers well to large-scale datasets such as ImageNet.

arXiv comment10 pages, 7 figures

References in corpus (8)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Improved Regularization of Convolutional Neural Networks with Cutout
• DARTS: Differentiable Architecture Search
• PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
• DeepArchitect: Automatically Designing and Training Deep Architectures
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
• AtomNAS: Fine-Grained End-to-End Neural Architecture Search
• Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks