|
Activity Number:
|
10
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #303286 |
|
Title:
|
Consensus Ranking Under the Exponential Model
|
|
Author(s):
|
Meila Marina*+
|
|
Companies:
|
University of Washington
|
|
Address:
|
Department of Statistics, Seattle, WA, 98195-4322,
|
|
Keywords:
|
|
|
Abstract:
|
We analyze a popular exponential model over rankings called the generalized Mallows model. Estimating the central ranking (or consensus ranking) of this model from data is NP-hard. We obtain the following new results: (1) We show that a standard search method can estimate both the central ranking \pi_0 and the model parameters \theta exactly. The search is n! in the worst case, but is tractable when the true distribution is concentrated around its mode. (2) From a statistical point of view, we show that the generalized Mallows model is jointly exponential in (\pi_0; \theta), and introduce the conjugate prior for this model class. (3) The sufficient statistics are the pairwise marginal probabilities that item i is preferred to item j. These probabilities are of interest in various applications. This paper provides the first exact tractable algorithm for their evaluation. Preliminary experiments confirm the theoretical predictions and compare the new algorithm and existing heuristics.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
