Diameter-based Interactive Structure Discovery
arXiv:1906.02101v23 citations
AI Analysis
This work provides a generic framework for interactive learning settings, but it is incremental as it builds on prior methods.
The paper tackles the problem of interactive structure discovery by adapting an existing active learning algorithm to be noise-tolerant and achieve favorable query complexity bounds.
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.