Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling

Abstract

We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models from the multinomial distribution on the policy vectors defined on the two search spaces independently. The proposed technique improves the efficiency of architecture search process significantly compared to the conventional methods based on reinforcement learning with the RNN controllers while achieving competitive accuracy and model size in target tasks. Our policy vectors are easily interpretable throughout the training procedure, which allows to analyze the search progress and the discovered architectures; the black-box characteristics of the RNN controllers hamper understanding training progress in terms of policy parameter updates. Our experiments demonstrate outstanding performance compared to the state-of-the-art methods with a fraction of search cost.

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• Recurrent Neural Network Regularization
• DARTS: Differentiable Architecture Search
• Efficient Neural Architecture Search via Parameter Sharing
• Large-Scale Evolution of Image Classifiers
• Neural Architecture Optimization
• Regularizing and Optimizing LSTM Language Models
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• The Evolved Transformer
• Learning to Optimize
• Graph HyperNetworks for Neural Architecture Search
• Breaking the Softmax Bottleneck: A High-Rank RNN Language Model
• You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
• Efficient Progressive Neural Architecture Search

Cited by in corpus (1)

• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap