AutoHAS: Efficient Hyperparameter and Architecture Search
This addresses the need for a unified and efficient search method for both hyperparameters and architectures in machine learning, though it appears incremental as it builds on existing search techniques.
The authors tackled the problem of efficiently searching for both hyperparameters and architectures in neural networks, proposing AutoHAS, which improved accuracy over popular architectures like ResNet and EfficientNet on datasets including CIFAR-10/100 and ImageNet.
Efficient hyperparameter or architecture search methods have shown remarkable results, but each of them is only applicable to searching for either hyperparameters (HPs) or architectures. In this work, we propose a unified pipeline, AutoHAS, to efficiently search for both architectures and hyperparameters. AutoHAS learns to alternately update the shared network weights and a reinforcement learning (RL) controller, which learns the probability distribution for the architecture candidates and HP candidates. A temporary weight is introduced to store the updated weight from the selected HPs (by the controller), and a validation accuracy based on this temporary weight serves as a reward to update the controller. In experiments, we show AutoHAS is efficient and generalizable to different search spaces, baselines and datasets. In particular, AutoHAS can improve the accuracy over popular network architectures, such as ResNet and EfficientNet, on CIFAR-10/100, ImageNet, and four more other datasets.