Few-Shot Bayesian Optimization with Deep Kernel SurrogatesDownload PDF

28 Sept 2020, 15:48 (modified: 25 Jan 2021, 20:47)ICLR 2021 PosterReaders: Everyone
Keywords: bayesian optimization, metalearning, few-shot learning, automl
Abstract: Hyperparameter optimization (HPO) is a central pillar in the automation of machine learning solutions and is mainly performed via Bayesian optimization, where a parametric surrogate is learned to approximate the black box response function (e.g. validation error). Unfortunately, evaluating the response function is computationally intensive. As a remedy, earlier work emphasizes the need for transfer learning surrogates which learn to optimize hyperparameters for an algorithm from other tasks. In contrast to previous work, we propose to rethink HPO as a few-shot learning problem in which we train a shared deep surrogate model to quickly adapt (with few response evaluations) to the response function of a new task. We propose the use of a deep kernel network for a Gaussian process surrogate that is meta-learned in an end-to-end fashion in order to jointly approximate the response functions of a collection of training data sets. As a result, the novel few-shot optimization of our deep kernel surrogate leads to new state-of-the-art results at HPO compared to several recent methods on diverse metadata sets.
One-sentence Summary: Model-agnostic meta-learning meets Bayesian optimization to speed-up hyperparameter optimization by learning on metadata from different data sets.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
12 Replies