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

2018/05/18 by Linnan Wang, Yiyang Zhao, Wang, Linnan +7 · 1 citation
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Distributed #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Parallel #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.1805.07440

openalex publication_date 2018/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

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.

Citations

• Continuous control with deep reinforcement learning
• Densely Connected Convolutional Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Neural Architecture Search with Reinforcement Learning
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Progressive Neural Architecture Search
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Efficient Neural Architecture Search via Parameter Sharing
• Neural Architecture Optimization
• ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
• Rethinking the Inception Architecture for Computer Vision
• A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• Aggregated Residual Transformations for Deep Neural Networks
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Data Classification with Dynamically Growing and Shrinking Neural Networks

Related

• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
• Prioritized Architecture Sampling with Monto-Carlo Tree Search
• Neural Architecture Search by Learning a Hierarchical Search Space
• Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
• Sample-Efficient Neural Architecture Search by Learning Action Space