The paper introduces a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than existing state-of-the-art methods based on reinforcement learning and evolutionary algorithms. The proposed method, called Progressive Neural Architecture Search (PNAS), uses a sequential model-based optimization (SMBO) strategy, where structures are searched in order of increasing complexity, and a surrogate model is learned to guide the search through the structure space. PNAS is shown to be up to 5 times more efficient than the reinforcement learning (RL) method of Zoph et al. (2018) in terms of the number of models evaluated, and 8 times faster in terms of total compute. The structures discovered by PNAS achieve state-of-the-art classification accuracies on CIFAR-10 and ImageNet datasets. The paper also discusses the architecture search space, the performance prediction with a surrogate model, and experimental results comparing PNAS to random search and the NAS method.The paper introduces a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than existing state-of-the-art methods based on reinforcement learning and evolutionary algorithms. The proposed method, called Progressive Neural Architecture Search (PNAS), uses a sequential model-based optimization (SMBO) strategy, where structures are searched in order of increasing complexity, and a surrogate model is learned to guide the search through the structure space. PNAS is shown to be up to 5 times more efficient than the reinforcement learning (RL) method of Zoph et al. (2018) in terms of the number of models evaluated, and 8 times faster in terms of total compute. The structures discovered by PNAS achieve state-of-the-art classification accuracies on CIFAR-10 and ImageNet datasets. The paper also discusses the architecture search space, the performance prediction with a surrogate model, and experimental results comparing PNAS to random search and the NAS method.