Computer Science – Learning
Scientific paper
2008-12-21
Computer Science
Learning
Scientific paper
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 of 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 $O(\log_2 k)$ 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.
Beygelzimer Alina
Langford J. J.
No associations
LandOfFree
The Offset Tree for Learning with Partial Labels does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with The Offset Tree for Learning with Partial Labels, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Offset Tree for Learning with Partial Labels will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-593106