2009 TheOffsetTreeforLearningwithPar

• (Beygelzimer et al., 2009) ⇒ Alina Beygelzimer, and John Langford. (2009). “The Offset Tree for Learning with Partial Labels.” In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2009). doi:10.1145/1557019.1557040

Subject Headings:

Cited By

• http://scholar.google.com/scholar?q=%22The+offset+tree+for+learning+with+partial+labels%22+2009
• http://portal.acm.org/citation.cfm?doid=1557019.1557040&preflayout=flat#citedby

Quotes

Abstract

We present an algorithm, called the Offset Tree, for learning to make decisions in situations where the payoff of only one choice is observed, rather than all choices. The algorithm reduces this setting to binary classification, allowing one to reuse any existing, fully supervised binary classification algorithm in this partial information setting. We show that the Offset Tree is an optimal reduction to binary classification. In particular, it has regret at most (k-1) times the regret of the binary classifier it uses (where k is the number of choices), and no reduction to binary classification can do better. This reduction is also computationally optimal, both at training and test time, requiring just O(log k) work to train on an example or make a prediction.
Experiments with the Offset Tree show that it generally performs better than several alternative approaches.

References

,

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2009 TheOffsetTreeforLearningwithPar	Alina Beygelzimer John Langford			The Offset Tree for Learning with Partial Labels		KDD-2009 Proceedings		10.1145/1557019.1557040		2009