Distance dependent Chinese restaurant processes
By David M. Blei, Peter I. Frazier. International Conference on Machine Learning, 2009
405 citations recorded by the source corpus.
We develop the distance dependent Chinese restaurant process (CRP), a flexible class of distributions over partitions that allows for non-exchangeability. This class can be used to model dependencies between data in infinite clustering models, including dependencies across time or space. We examine the properties of the distance dependent CRP, discuss its connections to Bayesian nonparametric mixture models, and derive a Gibbs sampler for both observed and mixture settings. We study its performance with time-dependent models and three text corpora. We show that relaxing the assumption of exchangeability with distance dependent CRPs can provide a better fit to sequential data. We also show its alternative formulation of the traditional CRP leads to a faster-mixing Gibbs sampling algorithm than the one based on the original formulation.
View Paper: https://www.semanticscholar.org/paper/2b2b87922d343d22c4872f2047f6ff6f88de6a43
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yura N. Perov
- Tuan Anh Le
- Frank D. Wood
- Khanh Nguyen
- Brendan T. O'Connor
- Jan-Willem van de Meent
- Dan Hendrycks
- Brooks Paige
Citations in the corpus
- Posterior calibration and exploratory analysis for natural language processing models (2015, background): “In a manner similar to a distance-dependent Chinese restaurant process (Blei and Frazier, 2011), it is non-parametric in the sense that the number of clusters M is not fixed in advance.”
- A Tutorial on Bayesian Nonparametric Models (2011, unknown): “We note in passing a burgeoning area of research attempting to devise more general specifications of dependencies in BNP models, particularly for DPs (MacEachern, 1999; Griffin and Steel, 2006; Blei and Frazier, 2010).”
- Why discourse affects speakers’ choice of referring expressions (2015, unknown): “rant Process (Blei and Frazier, 2011).”
- Data-driven Sequential Monte Carlo in Probabilistic Programming (2015, background): “In addition, the proposal that we implemented is related to the distance dependent Chinese restaurant process (DDCRP) [1].”