Paper: A Note on the Implementation of Hierarchical Dirichlet Processes

ACL ID P09-2085
Title A Note on the Implementation of Hierarchical Dirichlet Processes
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2009
Authors

The implementation of collapsed Gibbs samplers for non-parametric Bayesian models is non-trivial, requiring con- siderable book-keeping. Goldwater et al. (2006a) presented an approximation which significantly reduces the storage and computation overhead, but we show here that their formulation was incorrect and, even after correction, is grossly inac- curate. We present an alternative formula- tion which is exact and can be computed easily. However this approach does not work for hierarchical models, for which case we present an efficient data structure which has a better space complexity than the naive approach.