Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search

Abstract

Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this paper, we present a novel scalable Monte Carlo Tree Search (MCTS) based NAS agent, named AlphaX, to tackle these two aspects. AlphaX improves the search efficiency by adaptively balancing the exploration and exploitation at the state level, and by a Meta-Deep Neural Network (DNN) to predict network accuracies for biasing the search toward a promising region. To amortize the network evaluation cost, AlphaX accelerates MCTS rollouts with a distributed design and reduces the number of epochs in evaluating a network by transfer learning, which is guided with the tree structure in MCTS. In 12 GPU days and 1000 samples, AlphaX found an architecture that reaches 97.84\% top-1 accuracy on CIFAR-10, and 75.5\% top-1 accuracy on ImageNet, exceeding SOTA NAS methods in both the accuracy and sampling efficiency. Particularly, we also evaluate AlphaX on NASBench-101, a large scale NAS dataset; AlphaX is 3x and 2.8x more sample efficient than Random Search and Regularized Evolution in finding the global optimum. Finally, we show the searched architecture improves a variety of vision applications from Neural Style Transfer, to Image Captioning and Object Detection.

arXiv commentTo appear in the Thirty-Fourth AAAI conference on Artificial Intelligence (AAAI-2020)

References in corpus (20)

• Continuous control with deep reinforcement learning
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Practical Bayesian Optimization of Machine Learning Algorithms
• Neural Architecture Search with Reinforcement Learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Densely Connected Convolutional Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Efficient Neural Architecture Search via Parameter Sharing
• Rethinking the Inception Architecture for Computer Vision
• Neural Architecture Optimization
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Aggregated Residual Transformations for Deep Neural Networks
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• Simple And Efficient Architecture Search for Convolutional Neural Networks
• Progressive Neural Architecture Search
• Net2Net: Accelerating Learning via Knowledge Transfer
• A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
• ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
• Convolution by Evolution: Differentiable Pattern Producing Networks

Cited by in corpus (5)

• AutoML: A Survey of the State-of-the-Art
• Sample-Efficient Neural Architecture Search by Learning Action Space
• Evaluating Efficient Performance Estimators of Neural Architectures
• A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
• Hyperparameter optimization with REINFORCE and Transformers