Chris Ying — accepted AI-conference papers

2019

NAS-Bench-101: Towards Reproducible Neural Architecture Search

Chris Ying, Aaron Klein, Eric Christiansen, Esteban Real, Kevin Murphy, Frank Hutter

ICML 2019oral

Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101,…

Cited by 905 Source ↗PDF ↗code ↗Scholar ↗

2018

Don't Decay the Learning Rate, Increase the Batch Size

Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying, Quoc V. Le

ICLR 2018poster

It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size during training. This procedure is successful for stochastic gradient descent (SGD), SGD with momentum, Nesterov momentum,…

Cited by 1362 Source ↗PDF ↗Scholar ↗