Text

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

While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings together the best of these two worlds by jointly and robustly optimizing the network architecture and the training hyperparameters to enable fully automated deep learning (AutoDL). Auto-PyTorch achieves state-of-the-art performance on several tabular benchmarks by combining multi-fidelity optimization with portfolio construction for warmstarting and ensembling of deep neural networks (DNNs) and common baselines for tabular data. To thoroughly study our assumptions on how to design such an AutoDL system, we additionally introduce a new benchmark on learning curves for DNNs, dubbed LCBench, and run extensive ablation studies of the full Auto-PyTorch on typical AutoML benchmarks, eventually showing that Auto-PyTorch performs better than several state-of-the-art competitors.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.43 No.9 September 2021

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 3079 - 3090

Bahasa

English

ISBN/ISSN

-

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

MACHINE LEARNING
BENTUK GALAKSI
NEURAL ARCHITECTURE SEARCH
AUTOMATED MACHINE LEARNING
HYPERPARAMETER OPTIMIZATION
MULTI-FIDELITY OPTIMIZATION
META-LEARNING

Info Detail Spesifik

DOI: 10.1109/TPAMI.2021.3067763

Pernyataan Tanggungjawab

Lucas Zimmer, Marius Lindauer, Frank Hutter

Versi lain/terkait

Lampiran Berkas

Komentar