Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery
This work addresses the need for diverse discoveries in adaptive experimental design, such as drug discovery, but is incremental as it builds on existing active search methods.
The paper tackles the problem of active search with multiple target classes by introducing a utility function that encourages diversity through diminishing returns, and demonstrates superior empirical performance in settings like drug discovery.
Active search is a setting in adaptive experimental design where we aim to uncover members of rare, valuable class(es) subject to a budget constraint. An important consideration in this problem is diversity among the discovered targets -- in many applications, diverse discoveries offer more insight and may be preferable in downstream tasks. However, most existing active search policies either assume that all targets belong to a common positive class or encourage diversity via simple heuristics. We present a novel formulation of active search with multiple target classes, characterized by a utility function chosen from a flexible family whose members encourage diversity via a diminishing returns mechanism. We then study this problem under the Bayesian lens and prove a hardness result for approximating the optimal policy for arbitrary positive, increasing, and concave utility functions. Finally, we design an efficient, nonmyopic approximation to the optimal policy for this class of utilities and demonstrate its superior empirical performance in a variety of settings, including drug discovery.