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

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

26 Mar 2019arXiv:1903.11059archive 2025-07-28

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

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.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

linnanwang/AlphaX-NASBench101 officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image CaptioningNeural Architecture SearchObject DetectionStyle TransferTransfer Learningobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search CIFAR-10 AlphaX-1 (cutout NASNet) Search Time (GPU days) 224 #33 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 AlphaX-1 (cutout NASNet) Top-1 Error Rate 2.82% #33 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification AlphaX-1 (cutout NASNet) Params 3.59M #19 of 19 Archive leaderboard report
Neural Architecture Search ImageNet AlphaX-1 Accuracy 75.5 #107 of 135 Archive leaderboard report
Neural Architecture Search ImageNet AlphaX-1 Params 5.4M #107 of 135 Archive leaderboard report
Neural Architecture Search ImageNet AlphaX-1 Top-1 Error Rate 24.5 #107 of 135 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Random Search

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections