2021/01/17 by Jingkang Wang, Wang, Jingkang, Mengye Ren +7
Computer Science · Decision Sciences · Mathematics · #Advanced Bandit Algorithms Research #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #cs.AI #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2101.06590
arxiv created 2021/01/17 · openalex publication_date 2021/01/17 · arxiv updated 2021/01/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters. However, these online HPO algorithms still require running evaluation on a set of validation examples at each training step, steeply increasing the training cost. To decide when to query the validation loss, we model online HPO as a time-varying Bayesian optimization problem, on top of which we propose a novel costly feedback setting to capture the concept of the query cost. Under this setting, standard algorithms are cost-inefficient as they evaluate on the validation set at every round. In contrast, the cost-efficient GP-UCB algorithm proposed in this paper queries the unknown function only when the model is less confident about current decisions. We evaluate our proposed algorithm by tuning hyperparameters online for VGG and ResNet on CIFAR-10 and ImageNet100. Our proposed online HPO algorithm reaches human expert-level performance within a single run of the experiment, while incurring only modest computational overhead compared to regular training.