Sample-Efficient Neural Architecture Search by Learning Actions for Monte Carlo Tree Search

Linnan Wang, Saining Xie, Teng Li, Rodrigo Fonseca, Yuandong Tian

Research output: Contribution to journalArticlepeer-review


Neural Architecture Search (NAS) has emerged as a promising technique for automatic neural network design. However, existing MCTS based NAS approaches often utilize manually designed action space, which is not directly related to the performance metric to be optimized (e.g., accuracy), leading to sample-inefficient explorations of architectures. To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics. During the search phase, as different action sequences lead to regions with different performance, the search efficiency can be significantly improved by biasing towards the good regions. On three NAS tasks, empirical results demonstrate that LaNAS is at least an order more sample efficient than baseline methods including evolutionary algorithms, Bayesian optimizations, and random search. When applied in practice, both one-shot and regular LaNAS consistently outperform existing results. Particularly, LaNAS achieves 99.0 percent accuracy on CIFAR-10 and 80.8 percent top1 accuracy at 600 MFLOPS on ImageNet in only 800 samples, significantly outperforming AmoebaNet with 33\times33× fewer samples. Our code is publicly available at

Original languageEnglish (US)
Pages (from-to)5503-5515
Number of pages13
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number9
StatePublished - Sep 1 2022


  • Monte Carlo tree search
  • Neural architecture search

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Sample-Efficient Neural Architecture Search by Learning Actions for Monte Carlo Tree Search'. Together they form a unique fingerprint.

Cite this