A New Perspective on Pool-Based Active Classification and False-Discovery Control

TL;DR

This paper introduces a novel, provably sample-efficient adaptive algorithm for identifying regions with high true positives and low false discovery rates, bridging gaps between classification, bandits, and FDR control.

Contribution

It presents the first provably sample-efficient adaptive method for false discovery control in search spaces, connecting classification, bandits, and FDR management.

Findings

Developed the first provably efficient adaptive algorithm for FDR control.

Established connections between classification, combinatorial bandits, and FDR.

Enhanced understanding of adaptive experimental design for false discovery minimization.

Abstract

In many scientific settings there is a need for adaptive experimental design to guide the process of identifying regions of the search space that contain as many true positives as possible subject to a low rate of false discoveries (i.e. false alarms). Such regions of the search space could differ drastically from a predicted set that minimizes 0/1 error and accurate identification could require very different sampling strategies. Like active learning for binary classification, this experimental design cannot be optimally chosen a priori, but rather the data must be taken sequentially and adaptively. However, unlike classification with 0/1 error, collecting data adaptively to find a set with high true positive rate and low false discovery rate (FDR) is not as well understood. In this paper we provide the first provably sample efficient adaptive algorithm for this problem. Along the way we highlight connections between classification, combinatorial bandits, and FDR control making contributions to each.