Timezone: »

XNAS: Neural Architecture Search with Expert Advice
Niv Nayman · Asaf Noy · Tal Ridnik · Itamar Friedman · Rong Jin · Lihi Zelnik

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #10

This paper introduces a novel optimization method for differential neural architecture search, based on the theory of prediction with expert advice. Its optimization criterion is well fitted for an architecture-selection, i.e., it minimizes the regret incurred by a sub-optimal selection of operations. Unlike previous search relaxations, that require hard pruning of architectures, our method is designed to dynamically wipe out inferior architectures and enhance superior ones. It achieves an optimal worst-case regret bound and suggests the use of multiple learning-rates, based on the amount of information carried by the backward gradients. Experiments show that our algorithm achieves a strong performance over several image classification datasets. Specifically, it obtains an error rate of 1.6% for CIFAR-10, 23.9% for ImageNet under mobile settings, and achieves state-of-the-art results on three additional datasets.

Author Information

Niv Nayman (Alibaba Group)
Asaf Noy (Alibaba)
Tal Ridnik (MIIL Alibaba)
Itamar Friedman (Alibaba)
Rong Jin (Alibaba)
Lihi Zelnik (Alibaba)

More from the Same Authors