Few-Shot Bayesian Optimization with Deep Kernel Surrogates

TL;DR

This paper introduces a few-shot Bayesian optimization approach using a deep kernel surrogate model that is meta-learned to quickly adapt to new hyperparameter tuning tasks, achieving state-of-the-art results.

Contribution

It proposes a novel deep kernel Gaussian process surrogate trained via meta-learning for rapid adaptation in hyperparameter optimization.

Findings

Achieves state-of-the-art HPO results on diverse datasets.

Demonstrates effective few-shot learning for hyperparameter tuning.

Outperforms recent transfer learning methods in HPO.

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.