Nonmyopic Multifidelity Active Search

Abstract

Active search is a learning paradigm where we seek to identify as many members of a rare, valuable class as possible given a labeling budget. Previous work on active search has assumed access to a faithful (and expensive) oracle reporting experimental results. However, some settings offer access to cheaper surrogates such as computational simulation that may aid in the search. We propose a model of multifidelity active search, as well as a novel, computationally efficient policy for this setting that is motivated by state-of-the-art classical policies. Our policy is nonmyopic and budget aware, allowing for a dynamic tradeoff between exploration and exploitation. We evaluate the performance of our solution on real-world datasets and demonstrate significantly better performance than natural benchmarks.

To appear in ICML 2021

References in corpus (5)

• Practical Bayesian Optimization of Machine Learning Algorithms
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Multi-fidelity Bayesian Optimisation with Continuous Approximations
• The Multi-fidelity Multi-armed Bandit