Talks
Fall 2015

# Learning Mixtures of Plackett-Luce Models

Friday, April 28th, 2017 4:30 pm5:00 pm

We prove that for any $k\geq 2$, the mixture of $k$ Plackett-Luce models for no more than $2k-1$ alternatives is non-identifiable and this bound is tight for $k=2$. For generic identifiability, we prove that the mixture of $k$ Plackett-Luce models over $m$ alternatives is {\em generically identifiable} if $k\leq\lfloor\frac {m-2} 2\rfloor!$.