# AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search

Source: [AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search](<https://www.sota2.com/research/paper/68fa66741e209131cea102ec>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:10:29.606Z

Authors: Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca

Published: 2019-03-26T04:54:53.000Z

## 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 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet (test) (Standard Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-test-standard-accuracy.md>): Image Classification; ImageNet (test); Top-1 Accuracy: 75.5.

- [Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1903.11059>)

[PDF](<https://arxiv.org/pdf/1903.11059.pdf>)

[Implementation](<https://drive.google.com/open?id=1DrqShLtuMwFPmLsR1YuXwVzvclnuwdmz>)
