Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search release_m643rptk55bafa6c2gwuzvrkaa

by Arber Zela, Aaron Klein, Stefan Falkner, Frank Hutter

Released as a article .

2018  

Abstract

While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimization and Hyperband for efficient joint neural architecture and hyperparameter search.
In text/plain format

Archived Files and Locations

application/pdf  699.6 kB
file_h47sno5herfhnbkbatu2257g2e
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-07-18
Version   v1
Language   en ?
arXiv  1807.06906v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 36e7e05d-af36-4495-8b7b-2c5748b0e0de
API URL: JSON