SOTAVerified

Progressive Neural Architecture Search

2017-12-02ECCV 2018Code Available0· sign in to hype

Chenxi Liu, Barret Zoph, Maxim Neumann, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space. Direct comparison under the same search space shows that our method is up to 5 times more efficient than the RL method of Zoph et al. (2018) in terms of number of models evaluated, and 8 times faster in terms of total compute. The structures we discover in this way achieve state of the art classification accuracies on CIFAR-10 and ImageNet.

Tasks

Evolutionary AlgorithmsGeneral ClassificationImage ClassificationNeural Architecture SearchReinforcement LearningReinforcement Learning (RL)

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
ImageNetPNASNet-5Top 1 Accuracy82.9—Unverified

Reproductions