Robust reductions from ranking to classification

Authors:
Maria-Florina Balcan;Nikhil Bansal;Alina Beygelzimer;Don Coppersmith;John Langford;Gregory B. Sorkin
Affiliations:
Carnegie Melon University, Pittsburgh, PA;IBM Thomas J. Watson Research Center, Yorktown Heights, Hawthorne, NY;IBM Thomas J. Watson Research Center, Yorktown Heights, Hawthorne, NY;IDA Center for Communications Research, Princeton, NJ;Yahoo Research, New York, NY;IBM Thomas J. Watson Research Center, Yorktown Heights, Hawthorne, NY
Venue:
COLT'07 Proceedings of the 20th annual conference on Learning theory
Year:
2007

Citing 7
Cited 11

An efficient boosting algorithm for combining preferences

The Journal of Machine Learning Research
Ordering by weighted number of wins gives a good ranking for weighted tournaments

SODA '06 Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm
Ranking Tournaments

SIAM Journal on Discrete Mathematics
Learning to order things

Journal of Artificial Intelligence Research
Ranking and scoring using empirical risk minimization

COLT'05 Proceedings of the 18th annual conference on Learning Theory
Stability and generalization of bipartite ranking algorithms

COLT'05 Proceedings of the 18th annual conference on Learning Theory
Margin-Based ranking meets boosting in the middle

COLT'05 Proceedings of the 18th annual conference on Learning Theory

Theory research at Google

ACM SIGACT News
Aggregating inconsistent information: Ranking and clustering

Journal of the ACM (JACM)
Smooth Boosting for Margin-Based Ranking

ALT '08 Proceedings of the 19th international conference on Algorithmic Learning Theory
Ordering by weighted number of wins gives a good ranking for weighted tournaments

ACM Transactions on Algorithms (TALG)
Reducing position-sensitive subset ranking to classification

Canadian AI'11 Proceedings of the 24th Canadian conference on Advances in artificial intelligence
Approximate reduction from AUC maximization to 1-norm soft margin optimization

ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Reduction from cost-sensitive ordinal ranking to weighted binary classification

Neural Computation
The K-armed dueling bandits problem

Journal of Computer and System Sciences
Generic subset ranking using binary classifiers

Theoretical Computer Science
Multi-prototype label ranking with novel pairwise-to-total-rank aggregation

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
A binary-classification-based metric between time-series distributions and its use in statistical and learning problems

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

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.