English

Conditional Probability Tree Estimation Analysis and Algorithms

Machine Learning 2014-08-12 v1 Machine Learning

Abstract

We consider the problem of estimating the conditional probability of a label in time O(log n), where n is the number of possible labels. We analyze a natural reduction of this problem to a set of binary regression problems organized in a tree structure, proving a regret bound that scales with the depth of the tree. Motivated by this analysis, we propose the first online algorithm which provably constructs a logarithmic depth tree on the set of labels to solve this problem. We test the algorithm empirically, showing that it works succesfully on a dataset with roughly 106 labels.

Keywords

Cite

@article{arxiv.1408.2031,
  title  = {Conditional Probability Tree Estimation Analysis and Algorithms},
  author = {Alina Beygelzimer and John Langford and Yuri Lifshits and Gregory Sorkin and Alexander L. Strehl},
  journal= {arXiv preprint arXiv:1408.2031},
  year   = {2014}
}

Comments

Appears in Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI2009)

R2 v1 2026-06-22T05:23:49.248Z