Scholars@Duke
Filippo Ascolani

Filippo Ascolani

Assistant Professor of Statistical Science
Statistical Science
filippo.ascolani@duke.edu
214 Old Chemistry, Box 90251, Durham, NC 27708-0251
415 Chapel Drive, 214 Old Chemistry, Durham, NC 27708-0251

Scholarly Works

Posterior concentration and adaptation of the mixing measure in Dirichlet process mixtures

Preprint · June 27, 2026 We study the asymptotic properties of the posterior on the latent space for infinite mixtures driven by a Dirichlet process, both in terms of mixing measure and clustering behaviour. In the well-specified regime, where the data are generated by a finite mi ... Link to item Cite

Scalability of Metropolis-within-Gibbs schemes for high-dimensional Bayesian models

Journal article Journal of the Royal Statistical Society Series B: Statistical Methodology · January 14, 2026 AbstractWe study general coordinate-wise Markov chain Monte Carlo schemes (such as Metropolis-within-Gibbs samplers), which are commonly used to fit Bayesian non-conjugate hierarchical models. We relate t ... Full text Cite

A Conversation with Mike West

Preprint · December 10, 2025 Mike West is currently the Arts & Sciences Distinguished Professor Emeritus of Statistics and Decision Sciences at Duke University. Mike's research in Bayesian analysis spans multiple interlinked areas: theory and methods of dynamic models in time series a ... Link to item Cite

A fast non-reversible sampler for Bayesian finite mixture models

Preprint · October 3, 2025 Finite mixtures are a cornerstone of Bayesian modelling, and it is well-known that sampling from the resulting posterior distribution can be a hard task. In particular, popular reversible Markov chain Monte Carlo schemes are often slow to converge when the ... Link to item Cite

Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression

Preprint · May 20, 2025 We investigate the convergence properties of popular data-augmentation samplers for Baye\-sian probit regression. Leveraging recent results on Gibbs samplers for log-concave targets, we provide simple and explicit non-asymptotic bounds on the associated mi ... Link to item Cite

An R Package for Nonparametric Inference on Dynamic Populations with Infinitely Many Types.

Journal article Journal of computational biology : a journal of computational molecular cell biology · December 2024 Fleming-Viot diffusions are widely used stochastic models for population dynamics that extend the celebrated Wright-Fisher diffusions. They describe the temporal evolution of the relative frequencies of the allelic types in an ideally infinite panmictic po ... Full text Cite

Entropy contraction of the Gibbs sampler under log-concavity

Preprint · October 1, 2024 The Gibbs sampler (a.k.a. Glauber dynamics and heat-bath algorithm) is a popular Markov Chain Monte Carlo algorithm which iteratively samples from the conditional distributions of a probability measure $π$ of interest. Under the assumption that $π$ is stro ... Link to item Cite

Nonparametric priors with full-range borrowing of information

Journal article Biometrika · September 1, 2024 Modelling of the dependence structure across heterogeneous data is crucial for Bayesian inference, since it directly impacts the borrowing of information. Despite extensive advances over the past two decades, most available methods only allow for nonnegati ... Full text Cite

DIMENSION-FREE MIXING TIMES OF GIBBS SAMPLERS FOR BAYESIAN HIERARCHICAL MODELS

Journal article Annals of Statistics · June 1, 2024 Gibbs samplers are popular algorithms to approximate posterior distributions arising from Bayesian hierarchical models. Despite their popularity and good empirical performance, however, there are still relatively few quantitative results on their convergen ... Full text Cite

Clustering consistency with Dirichlet process mixtures

Journal article Biometrika · May 15, 2023 SummaryDirichlet process mixtures are flexible nonparametric models, particularly suited to density estimation and probabilistic clustering. In this work we study the posterior distribution induced by Dirichlet process mixt ... Full text Cite

Dimension-free mixing times of Gibbs samplers for Bayesian hierarchical models

Preprint · April 14, 2023 Gibbs samplers are popular algorithms to approximate posterior distributions arising from Bayesian hierarchical models. Despite their popularity and good empirical performances, however, there are still relatively few quantitative results on their converge ... Link to item Cite