Papers › Sample-Efficient Neural Architecture Search by Learning Action Space for Monte Carlo...

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

1 Jan 2019archive 2025-07-28

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

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 outperforms existing results. Particularly, LaNAS achieves 99.0\% accuracy on CIFAR-10 and 80.8\% top1 accuracy at 600 MFLOPS on ImageNet in only 800 samples, significantly outperforming AmoebaNet with 33× fewer samples.

PaperPDFCode

Code

facebookresearch/LaMCTS pytorchNOASSERTION 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

Evolutionary AlgorithmsImage ClassificationNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 LaNet Percentage correct 99.03 #20 of 265 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.

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