Markov Chain Sampling Methods for Dirichlet Process Mixture Models

By Radford M. Neal. 2000

2,684 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning (2020, methodology): “If we additionally condition xn and reflect the likelihood, we obtain (Neal, 2000): θn+1|θ1, .”
Variational inference for Dirichlet process mixtures (2006, methodology): “MCMC provides one class of approximations for this posterior and the predictive density (MacEachern 1994; Escobar and West 1995; Neal 2000).”
Towards total scene understanding: Classification, annotation and segmentation in an automatic framework (2009, methodology): “To this end, we derive a collapsed Gibbs sampling algorithm [24].”
PhyloBayes MPI: phylogenetic reconstruction with infinite mixtures of profiles in a parallel environment. (2013, background): “2010) than the classical Chinese restaurant representation (Neal 2000).”
The Indian Buffet Process: An Introduction and Review (2011, methodology): “For details, and alternative algorithms that can be used when this assumption is violated, see Neal (2000).”
Bayesian mixture modeling for spatial Poisson process intensities, with applications to extreme value analysis (2007, methodology): “Several posterior simulation methods have been suggested in the literature for sampling from the marginal posterior that results after integrating out the random mixing distribution in a DP mixture model (see, e.g., Escobar and West, 1998; MacEachern, 1998; Neal, 2000).”
Distance dependent Chinese restaurant processes (2009, neutral): “Each panel illustrates 100 Gibbs runs using Algorithm 3 of (Neal, 2000) (CRP, in blue) and the sampler from Section 3 with the identity decay function (distance dependent CRP, in red).”
Coresets for Nonparametric Estimation - the Case of DP-Means (2015, methodology): “By analyzing the case where σ approaches zero, Kulis & Jordan (2012) show that the Gibbs sampler of Neal (2000) converges to a hard clustering algorithm.”
Bayesian reasoning and machine learning (2012, neutral): “A detailed discussion of these techniques is beyond the scope of this book and we refer the reader to [165] for a deterministic (variational) approach and [206] for a discussion of sampling approaches.”
Infinite Markov-Switching Maximum Entropy Discrimination Machines (2013, methodology): “Motivated by these results, formulation of our model is based on the introduction of appropriate nonparametric priors over the employed large-margin component classifiers of our model.”
Reconciling meta-learning and continual learning with online mixtures of tasks (2018, methodology): “The most widely used is the Gibbs sampler [35, 17], which draws from the conditional distribution of each latent variable, given the others, until convergence to the posterior distribution over all the latents.”
Bayesian Nonparametric Modelling of the Return Distribution with Stochastic Volatility (2011, neutral): “Many efficient MCMC sampling schemes for these models have been developed (Escobar and West 1995; Neal 2000).”
Rational approximations to rational models: alternative algorithms for category learning. (2010, methodology): “The particle filter for the DPMM is initialized with the first stimulus assigned to the first cluster for all M particles, in this case M ϭ 2.”
Infinite latent feature models and the Indian buffet process (2005, methodology): “The distribution over partitions implied by the CRP can be de rived by taking the limit of the probability of the corresponding equivalence class of a ssignment vectors in a model where class assignments are generated from a multinomial di stribution with a Dirichlet prior [9, 10].”
Stochastic variational inference (2012, background): “Approximate posterior inference for BNP models in general is an active ﬁeld of research (Escobar and West, 1995; Neal, 2000; Blei and Jordan, 2006; Teh et al., 2007).”