Towards Automated Deep Learning: Efficient Joint Neural Architecture and
Hyperparameter Search
release_m643rptk55bafa6c2gwuzvrkaa
by
Arber Zela, Aaron Klein, Stefan Falkner, Frank Hutter
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) |
1807.06906v1
access all versions, variants, and formats of this works (eg, pre-prints)