Hyperparameter Optimization with Differentiable Metafeatures

arxiv(2021)

引用 0|浏览19
暂无评分
摘要
Metafeatures, or dataset characteristics, have been shown to improve the performance of hyperparameter optimization (HPO). Conventionally, metafeatures are precomputed and used to measure the similarity between datasets, leading to a better initialization of HPO models. In this paper, we propose a cross dataset surrogate model called Differentiable Metafeature-based Surrogate (DMFBS), that predicts the hyperparameter response, i.e. validation loss, of a model trained on the dataset at hand. In contrast to existing models, DMFBS i) integrates a differentiable metafeature extractor and ii) is optimized using a novel multi-task loss, linking manifold regularization with a dataset similarity measure learned via an auxiliary dataset identification meta-task, effectively enforcing the response approximation for similar datasets to be similar. We compare DMFBS against several recent models for HPO on three large meta-datasets and show that it consistently outperforms all of them with an average 10% improvement. Finally, we provide an extensive ablation study that examines the different components of our approach.
更多
查看译文
关键词
differentiable metafeatures,optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要