Robust Reductions from Ranking to Classification

Abstract. We reduce ranking, as measured by the Area Under the Receiver Operating Characteristic Curve (AUC), to binary classification. The core theorem shows that a binary classification regret of r on the induced binary problem implies an AUC regret of at most 2r. This is a large improvement over approaches such as ordering according to regressed scores, which have a regret transform of r nr where n is the number of elements.

• Type: Conference
• Year: 2007
• Where: COLT
• Authors: Maria-Florina Balcan, Nikhil Bansal, Alina Beygelzimer, Don Coppersmith, John Langford, Gregory B. Sorkin
• Keywords: Binary Classification, Binary Classification Regret, COLT 2007, Machine Learning, Receiver Operating Characteristic Curve