Lifelong Bayesian Optimization

TL;DR

Lifelong Bayesian Optimization (LBO) is an online, multitask Bayesian optimization method that efficiently leverages past data to improve model selection for evolving datasets in Auto-ML systems.

Contribution

The paper introduces LBO, a scalable lifelong BO algorithm that uses past optimizations to accelerate current model selection tasks for dynamic datasets.

Findings

LBO outperforms standard Bayesian Optimization in experiments.

LBO effectively leverages past data to improve current optimization.

LBO scales well with increasing data and optimization tasks.

Abstract

Automatic Machine Learning (Auto-ML) systems tackle the problem of automating the design of prediction models or pipelines for data science. In this paper, we present Lifelong Bayesian Optimization (LBO), an online, multitask Bayesian optimization (BO) algorithm designed to solve the problem of model selection for datasets arriving and evolving over time. To be suitable for "lifelong" Bayesian Optimization, an algorithm needs to scale with the ever increasing number of acquisitions and should be able to leverage past optimizations in learning the current best model. We cast the problem of model selection as a black-box function optimization problem. In LBO, we exploit the correlation between functions by using components of previously learned functions to speed up the learning process for newly arriving datasets. Experiments on real and synthetic data show that LBO outperforms standard BO algorithms applied repeatedly on the data.