Robust reductions from ranking to classification

  title={Robust reductions from ranking to classification},
  author={Maria-Florina Balcan and Nikhil Bansal and Alina Beygelzimer and Don Coppersmith and John Langford and Gregory B. Sorkin},
  journal={Machine Learning},
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. 
Highly Influential
This paper has highly influenced a number of papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 101 citations. REVIEW CITATIONS



Citations per Year

101 Citations

Semantic Scholar estimates that this publication has 101 citations based on the available data.

See our FAQ for additional information.