AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

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

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

TPAMI 2021 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 99 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use learned latent actions instead of manual actionsMCTS NAS · NASBench-101speedup vs random search: 700x fasterImproved
use learned latent actions instead of random searchMCTS NAS · ConvNet-60Kspeedup vs random search: 22x fasterImproved
learn actions (LaNAS) vs second best baselineNAS search · NASBench-101final test error (%): 0.137% -> 0.011%Improved
use global action space instead of sequential action space (ablation)MCTS · CIFAR-10 plain CNN motivating examplesearch speedImproved
use linear classifier instead of MLP for splitting (ablation)LaNAS · NASBench-101samples to optimumImproved
increase tree height (ablation)LaNAS · NASBench-101samples to find optimumImproved
decrease number of selects per iteration (ablation)LaNAS · NASBench-101samples to find optimumImproved
add random initialization samples (init > 0) (ablation)LaNAS · NASBench-101search performanceImproved
use init=2000 instead of init=100-400 (ablation)LaNAS · NASBench-101time to top 5%Hurt
add exploration term c from 0 to 0.1 in UCB (ablation)LaNAS · NASBench-101search performanceImproved
use large c above 0.5 in UCB (ablation)LaNAS · NASBench-101search performanceHurt
use Bayesian sampling instead of random sampling within partition (ablation)LaNAS · NASBench-101final resultMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy