Diameter-based Interactive Structure Discovery

TL;DR

This paper presents a versatile framework for interactive structure discovery, unifying various learning tasks, and adapts an active learning algorithm to be noise-tolerant with efficient query complexity.

Contribution

It introduces a generic framework for interactive structure discovery and adapts an existing active learning algorithm to handle noise effectively.

Findings

Algorithm is noise-tolerant

Achieves favorable query complexity bounds

Unifies multiple interactive learning tasks

Abstract

We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interactive drug discovery, and others. We adapt a recently developed active learning algorithm of Tosh and Dasgupta (2017) for interactive structure discovery, and show that the new algorithm can be made noise-tolerant and enjoys favorable query complexity bounds.