AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

PyGlove: Symbolic Programming for Automated Machine Learning

Daiyi Peng, Xuanyi Dong, Esteban Real, Mingxing Tan, Yifeng Lu, Gabriel Bender, Hanxiao Liu, Adam Kraft, Chen Liang, Quoc V. Le

NeurIPS 2020 · Architectures and efficiency › Neural architecture search · approach: AutoML pipeline search · 7 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
Search kernel size and expansion ratio with Random SearchMobileNetV2 · ImageNet validationaccuracy: 73.1 -> 73.7Improved
Use Bayesian search instead of Random Search on S1MobileNetV2 · ImageNet validationaccuracy: 73.7 -> 73.9Improved
Use TuNAS instead of Bayesian search on S1MobileNetV2 · ImageNet validationaccuracy: 73.9 -> 74.2Improved
Search output filters with TuNASMobileNetV2 · ImageNet validationaccuracy: 73.1 -> 73.3Improved
Combine kernel size, expansion ratio, and output-filter searchMobileNetV2 · ImageNet validationaccuracy: 73.1 -> 73.8Improved
Factorize search into node optimization followed by edge optimizationNAS-Bench-101 search with Regularized Evolution · NAS-Bench-101CIFAR-10 test accuracyHurt
Use a hybrid flow: optimize nodes first, then edges using the best node settingNAS-Bench-101 search with Regularized Evolution · NAS-Bench-101CIFAR-10 test accuracyImproved

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