It has become increasingly easy nowadays to collect approximate posterior samples via fast algorithms such as variational Bayes, but concerns exist about the estimation accuracy. It is tempting to build solutions that exploit approximate samples in a canonical Markov chain Monte Carlo framework. As the dimension increases, a major barrier is that the approximate sample tends to have a low Metropolis--Hastings acceptance rate when used as a proposal. In this article, we propose a simple solution named graph-accelerated Markov Chain Monte Carlo. We build a graph with each node assigned to an approximate sample, then run Markov chain Monte Carlo with random walks over the graph. We optimize the graph edges to enforce small differences in posterior density/probability between nodes, while encouraging edges to have large distances in the parameter space. The graph allows us to accelerate a canonical Markov transition kernel through mixing with a large-jump Metropolis-Hastings step. The acceleration is easily applicable to existing Markov chain Monte Carlo algorithms. We theoretically quantify the rate of acceptance as dimension increases, and show the effects on improved mixing time. We demonstrate improved mixing performances for challenging problems, such as those involving multiple modes, non-convex density contour, or large-dimension latent variables.

In multivariate data analysis, it is often important to estimate a graph characterizing dependence among $p$ variables. A popular strategy in Gaussian graphical models and latent Gaussian graphical models uses the non-zero entries in a $p\times p$ covariance or precision matrix, typically requiring restrictive modeling assumptions for accurate graph recovery. To improve model robustness, we instead focus on estimating the backbone of the dependence graph. We use a spanning tree likelihood, based on a minimalist graphical model that is purposely overly-simplified. Taking a Bayesian approach, we place a prior on the space of trees and quantify uncertainty in the graphical model. In both theory and experiments, we show that this model does not require the population graph to be a spanning tree or the covariance to satisfy assumptions beyond positive-definiteness. The model accurately recovers the backbone of the population graph at a rate competitive with existing approaches but with better robustness. We show combinatorial properties of the spanning tree, which may be of independent interest, and develop an efficient Gibbs sampler for Bayesian inference. Analyzing electroencephalography data using a hidden Markov model with each latent state modeled by a spanning tree, we show that results are much more interpretable compared with popular alternatives.

In network analysis, it is common to work with a collection of graphs that exhibit heterogeneity. For example, neuroimaging data from patient cohorts are increasingly available. A critical analytical task is to identify communities, and graph Laplacian-based methods are routinely used. However, these methods are currently limited to a single network and also do not provide measures of uncertainty on the community assignment. In this work, we first propose a probabilistic network model called the ”Spiked Laplacian Graph” that considers an observed network as a transform of the Laplacian and degree matrices of the network generating process, with the Laplacian eigenvalues modeled by a modified spiked structure. This effectively reduces the number of parameters in the eigenvectors, and their sign patterns allow efficient estimation of the underlying community structure. Further, the posterior distribution of the eigenvectors provides uncertainty quantification for the community estimates. Second, we introduce a Bayesian non-parametric approach to address the issue of heterogeneity in a collection of graphs. Theoretical results are established on the posterior consistency of the procedure and provide insights on the trade-off between model resolution and accuracy. We illustrate the performance of the methodology on synthetic data sets, as well as a neuroscience study related to brain activity in working memory.

Vector autoregression has been widely used for modeling and analysis of multivariate time series data. In high-dimensional settings, model parameter regularization schemes inducing sparsity yield interpretable models and achieved good forecasting performance. However, in many data applications, such as those in neuroscience, the Granger causality graph estimates from existing vector autoregression methods tend to be quite dense and difficult to interpret, unless one compromises on the goodness-of-fit. To address this issue, this paper proposes to incorporate a commonly used structural assumption --- that the ground-truth graph should be largely connected, in the sense that it should only contain at most a few components. We take a Bayesian approach and develop a novel tree-rank prior distribution for the regression coefficients. Specifically, this prior distribution forces the non-zero coefficients to appear only on the union of a few spanning trees. Since each spanning tree connects $p$ nodes with only $(p-1)$ edges, it effectively achieves both high connectivity and high sparsity. We develop a computationally efficient Gibbs sampler that is scalable to large sample size and high dimension. In analyzing test-retest functional magnetic resonance imaging data, our model produces a much more interpretable graph estimate, compared to popular existing approaches. In addition, we show appealing properties of this new method, such as efficient computation, mild stability conditions and posterior consistency.

In mixture modeling and clustering applications, the number of components and clusters is often not known. A stick-breaking mixture model, such as the Dirichlet process mixture model, is an appealing construction that assumes infinitely many components, while shrinking the weights of most of the unused components to near zero. However, it is well-known that this shrinkage is inadequate: even when the component distribution is correctly specified, spurious weights appear and give an inconsistent estimate of the number of clusters. In this article, we propose a simple solution: when breaking each mixture weight stick into two pieces, the length of the second piece is multiplied by a quasi-Bernoulli random variable, taking value one or a small constant close to zero. This effectively creates a soft truncation and further shrinks the unused weights. Asymptotically, we show that as long as this small constant diminishes to zero at a rate faster than $o(1/n^2)$, with $n$ the sample size and given data from a finite mixture model, the posterior distribution will converge to the true number of clusters. In comparison, we rigorously explore Dirichlet process mixture models using a concentration parameter that is either constant or rapidly diminishes to zero---both of which lead to inconsistency for the number of clusters. Our proposed model is easy to implement, requiring only a small modification of a standard Gibbs sampler for mixture models. In simulations and a data application of clustering brain networks, our proposed method recovers the ground-truth number of clusters, and leads to a small number of clusters.

Model-based clustering is widely used in a variety of application areas. However, fundamental concerns remain about robustness. In particular, results can be sensitive to the choice of kernel representing the within-cluster data density. Leveraging on properties of pairwise differences between data points, we propose a class of Bayesian distance clustering methods, which rely on modeling the likelihood of the pairwise distances in place of the original data. Although some information in the data is discarded, we gain substantial robustness to modeling assumptions. The proposed approach represents an appealing middle ground between distance- and model-based clustering, drawing advantages from each of these canonical approaches. We illustrate dramatic gains in the ability to infer clusters that are not well represented by the usual choices of kernel. A simulation study is included to assess performance relative to competitors, and we apply the approach to clustering of brain genome expression data.

High dimensional data often contain multiple facets, and several clustering patterns can co-exist under different variable subspaces, also known as the views. While multi-view clustering algorithms were proposed, the uncertainty quantification remains difficult --- a particular challenge is in the high complexity of estimating the cluster assignment probability under each view, and sharing information among views. In this article, we propose an approximate Bayes approach --- treating the similarity matrices generated over the views as rough first-stage estimates for the co-assignment probabilities; in its Kullback-Leibler neighborhood, we obtain a refined low-rank matrix, formed by the pairwise product of simplex coordinates. Interestingly, each simplex coordinate directly encodes the cluster assignment uncertainty. For multi-view clustering, we let each view draw a parameterization from a few candidates, leading to dimension reduction. With high model flexibility, the estimation can be efficiently carried out as a continuous optimization problem, hence enjoys gradient-based computation. The theory establishes the connection of this model to a random partition distribution under multiple views. Compared to single-view clustering approaches, substantially more interpretable results are obtained when clustering brains from a human traumatic brain injury study, using high-dimensional gene expression data.

There has been considerable interest in making Bayesian inference more scalable. In big data settings, most of the focus has been on reducing the computing time per iteration rather than reducing the number of iterations needed in Markov chain Monte Carlo (MCMC). This article considers data augmentation MCMC (DA-MCMC), a widely used technique. DA-MCMC samples tend to become highly autocorrelated in large samples, due to a mis-calibration problem in which conditional posterior distributions given augmented data are too concentrated. This makes it necessary to collect very long MCMC paths to obtain acceptably low MC error. To combat this inefficiency, we propose a family of calibrated data augmentation algorithms, which appropriately adjust the variance of conditional posterior distributions. A Metropolis-Hastings step is used to eliminate bias in the stationary distribution of the resulting sampler. Compared to existing alternatives, this approach can dramatically reduce MC error by reducing autocorrelation and increasing the effective number of DA-MCMC samples per unit of computing time. The approach is simple and applicable to a broad variety of existing data augmentation algorithms. We focus on three popular generalized linear models: probit, logistic and Poisson log-linear. Dramatic gains in computational efficiency are shown in applications.