Library Header Image
LSE Research Online LSE Library Services

Conditional probability tree estimation analysis and algorithms

Beygelzimer, Alina, Langford, John, Lifshits, Yuri, Sorkin, Gregory B. ORCID: 0000-0003-4935-7820 and Strehl, Alex (2009) Conditional probability tree estimation analysis and algorithms. In: Uncertainty in artificial intelligence, 2009-06-18 - 2009-06-21, QC, Canada, CAN.

Full text not available from this repository.


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 $10^6$ labels.

Item Type: Conference or Workshop Item (Paper)
Official URL:
Additional Information: © 2009 the Authors
Divisions: Management
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Date Deposited: 13 May 2011 10:37
Last Modified: 16 May 2024 11:03

Actions (login required)

View Item View Item