AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL

Lucas Zimmer, Marius Lindauer, Frank Hutter

TPAMI 2021 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 248 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 BOHB multi-fidelity instead of plain BO (ablation)Auto-PyTorch · 8 meta-test OpenML datasetsanytime performance: BOHB performed as well or better than plain BOImproved
add greedy portfolio warmstarting (ablation)Auto-PyTorch BOHB · 8 meta-test OpenML datasetsanytime performanceImproved
add simple portfolio of all 100 incumbents (ablation)Auto-PyTorch BOHB · 8 meta-test OpenML datasetsanytime performanceMixed
add ensembles of DNNs across fidelities (ablation)Auto-PyTorch · 8 meta-test OpenML datasetserror over timeImproved
add diverse ensembles including RF, ExtraTrees, LightGBM, CatBoost, KNN (ablation)Auto-PyTorch · 8 meta-test OpenML datasetserror over timeImproved
add ensembling (ablation)Auto-PyTorch Tabular · covertypeaccuracy (%): 93.35 -> 96.86Improved
add ensembling (ablation)Auto-PyTorch Tabular · dilbertaccuracy (%): 98.54 -> 98.70Improved
add ensembling (ablation)Auto-PyTorch Tabular · caraccuracy (%): 98.59 -> 96.41Hurt
run 3 parallel workers instead of sequentialAuto-PyTorch BOHB · larger OpenML datasetsspeedup: speedups of 3x or moreImproved
use Auto-PyTorch Tabular instead of AutoNet2.0Auto-PyTorch · covertypemisclassification rate (%): 31.78% -> 3.14%Improved
use adaptive instead of non-adaptive learning rate schedule (ablation)LCBench configs · budget pair (12, 50)Spearman rank correlation: 0.91 -> 0.88Hurt
use adaptive instead of non-adaptive learning rate schedule (ablation)LCBench configs · budget pair (12, 25)Spearman rank correlation: 0.94 -> 0.95No clear effect

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