The offset tree for learning with partial labels

9 years 10 months ago
The offset tree for learning with partial labels
We present an algorithm, called the offset tree, for learning in situations where a loss associated with different decisions is not known, but was randomly probed. The algorithm is an optimal reduction from this problem 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 decisions, and no reduction to binary classification can do better. We test the offset tree empirically and discover that it generally results in superior (or equal) performance, compared to several plausible alternative approaches.
Alina Beygelzimer, John Langford
Added 25 Nov 2009
Updated 25 Nov 2009
Type Conference
Year 2009
Where KDD
Authors Alina Beygelzimer, John Langford
Comments (0)