The offset tree for learning with partial labels

  title={The offset tree for learning with partial labels},
  author={Alina Beygelzimer and John Langford},
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… CONTINUE READING
Highly Influential
This paper has highly influenced 11 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 67 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 3 times over the past 90 days. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.

67 Citations

Citations per Year
Semantic Scholar estimates that this publication has 67 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.

Data Mining: Practical machine l earning tools with Java implementations, 2000:

  • I. Witten, E. Frank
  • 2000
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…