XNAS: Neural Architecture Search with Expert Advice
This work addresses the challenge of efficient and effective neural architecture search for image classification, representing an incremental improvement over previous methods.
The paper tackles the problem of neural architecture search by introducing a novel optimization method based on prediction with expert advice, which dynamically eliminates inferior architectures and enhances superior ones, achieving error rates of 1.6% on CIFAR-10 and 24% on ImageNet under mobile settings.
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, 24% for ImageNet under mobile settings, and achieves state-of-the-art results on three additional datasets.