Posterior contraction of the population polytope in finite admixture models

@article{Nguyen2012PosteriorCO,
  title={Posterior contraction of the population polytope in finite admixture models},
  author={XuanLong Nguyen},
  journal={ArXiv},
  year={2012},
  volume={abs/1206.0068}
}
  • X. Nguyen
  • Published 1 June 2012
  • Computer Science, Mathematics
  • ArXiv
We study the posterior contraction behavior of the latent population structure that arises in admixture models as the amount of data increases. We adopt the geometric view of admixture models - alternatively known as topic models - as a data generating mechanism for points randomly sampled from the interior of a (convex) population polytope, whose extreme points correspond to the population structure variables of interest. Rates of posterior contraction are established with respect to Hausdorff… 
Convergence Rates of Latent Topic Models Under Relaxed Identifiability Conditions
  • Yining Wang
  • Computer Science, Mathematics
    Electronic Journal of Statistics
  • 2019
TLDR
The maximum likelihood estimator converges to one of the finitely many equivalent parameters in Wasserstein's distance metric at a rate of $n^{-1/4}$ without assuming separability or non-degeneracy of the underlying topics and/or the existence of more than three words per document, thus generalizing the previous works of Anandkumar et al. (2012, 2014).
On posterior contraction of parameters and interpretability in Bayesian mixture modeling
We study posterior contraction behaviors for parameters of interest in the context of Bayesian mixture modeling, where the number of mixing components is unknown while the model itself may or may not
Streaming dynamic and distributed inference of latent geometric structures
TLDR
This work develops new models and algorithms for learning the temporal dynamics of the topic polytopes and related geometric objects that arise in topic model based inference through the connection between the modeling of topic polytope evolution, Beta-Bernoulli process and Hungarian matching algorithm.
Scalable inference of topic evolution via models for latent geometric structures
TLDR
This work develops new models and algorithms for learning the temporal dynamics of the topic polytopes and related geometric objects that arise in topic model based inference through the connection between the modeling of topic polytope evolution, Beta-Bernoulli process and the Hungarian matching algorithm.
Conic Scan-and-Cover algorithms for nonparametric topic modeling
TLDR
These algorithms are shown in practice to have accuracy comparable to a Gibbs sampler in terms of topic estimation, which requires the number of topics be given, and to be one of the fastest among several state of the art parametric techniques.
Minimum Volume Topic Modeling
TLDR
A convex relaxation of the minimum volume topic model optimization is proposed, and it is shown that the relaxed problem has the same global minimum as the original problem under the separability assumption and the sufficiently scattered assumption.
When are overcomplete topic models identifiable? uniqueness of tensor tucker decompositions with structured sparsity
TLDR
This paper specifies which overcomplete models can be identified given observable moments of a certain order, and establishes that random structured topic models are identifiable w.h.p. in the overcomplete regime.
J an 2 01 5 Borrowing strengh in hierarchical Bayes : convergence of the Dirichlet base measure 1
This paper studies posterior concentration behavior of the bas probability measure of a Dirichlet measure, given observations asso ciated with the sampled Dirichlet processes, as the number of
When are Overcomplete Representations Identifiable? Uniqueness of Tensor Decompositions Under Expansion Constraints
Abstract : Overcomplete latent representations have been very popular for unsupervised feature learning in recent years. In this paper, we specify which overcomplete models can be identified given
Multilevel Clustering via Wasserstein Means
We propose a novel approach to the problem of multilevel clustering, which aims to simultaneously partition data in each group and discover grouping patterns among groups in a potentially large
...
1
2
3
4
...

References

SHOWING 1-10 OF 34 REFERENCES
Asymptotic behaviour of the posterior distribution in overfitted mixture models
Abstract Summary.  We study the asymptotic behaviour of the posterior distribution in a mixture model when the number of components in the mixture is larger than the true number of components: a
Convergence of latent mixing measures in finite and infinite mixture models
This paper studies convergence behavior of latent mixing measures that arise in finite and infinite mixture models, using transportation distances (i.e., Wasserstein metrics). The relationship
Bayesian Model Selection in Finite Mixtures by Marginal Density Decompositions
We consider the problem of estimating the number of components d and the unknown mixing distribution in a finite mixture model, in which d is bounded by some fixed finite number N. Our approach
The consistency of posterior distributions in nonparametric problems
We give conditions that guarantee that the posterior probability of every Hellinger neighborhood of the true distribution tends to 1 almost surely. The conditions are (1) a requirement that the prior
On rates of convergence for posterior distributions in infinite-dimensional models
This paper introduces a new approach to the study of rates of convergence for posterior distributions. It is a natural extension of a recent approach to the study of Bayesian consistency. Crucially,
Convergence rates of posterior distributions for non-i.i.d. observations
We consider the asymptotic behavior of posterior distributions and Bayes estimators based on observations which are required to be neither independent nor identically distributed. We give general
On nonparametric estimation of density level sets
Let X 1 ,...,X n be independent identically distributed observations from an unknown probability density f(.). Consider the problem of estimating the level set G = G f (λ) = {x ∈ R 2 : f(x) ≥ λ} from
Rates of convergence of posterior distributions
We compute the rate at which the posterior distribution concentrates around the true parameter value. The spaces we work in are quite general and include infinite dimensional cases. The rates are
Optimal Rate of Convergence for Finite Mixture Models
In finite mixture models, we establish the best possible rate of convergence for estimating the mixing distribution. We find that the key for estimating the mixing distribution is the knowledge of
A Spectral Algorithm for Latent Dirichlet Allocation
TLDR
This work provides a simple and efficient learning procedure that is guaranteed to recover the parameters for a wide class of multi-view models and topic models, including latent Dirichlet allocation (LDA).
...
1
2
3
4
...