Simple and efficient architecture search for Convolutional Neural Networks

Thomas Elsken, Jan Hendrik Metzen, Frank Hutter

Keywords: Deep Learning, Hyperparameter Optimization, Architecture Search, Convolutional Neural Networks, Network Morphism, Network Transformation, SGDR, Cosine annealing, hill climbing

TL;DR: We propose a simple and efficent method for architecture search for convolutional neural networks.

Abstract:

Neural networks have recently had a lot of success for many tasks. However, neural
network architectures that perform well are still typically designed manually
by experts in a cumbersome trial-and-error process. We propose a new method
to automatically search for well-performing CNN architectures based on a simple
hill climbing procedure whose operators apply network morphisms, followed
by short optimization runs by cosine annealing. Surprisingly, this simple method
yields competitive results, despite only requiring resources in the same order of
magnitude as training a single network. E.g., on CIFAR-10, our method designs
and trains networks with an error rate below 6% in only 12 hours on a single GPU;
training for one day reduces this error further, to almost 5%.

Code: [ 3 community implementations](https://paperswithcode.com/paper/?openreview=SySaJ0xCZ)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1711.04528/code)