Stefano Favaro

Bayesian Regularization of the Length of Memory in Reversible Sequences

2015 · Journal of the Royal Statistical Society Series B (Statistical Methodology)

Summary Variable order Markov chains have been used to model discrete sequential data in a variety of fields. A host of methods exist to estimate the history-dependent lengths of memory which characterize these models and …

A hybrid sampler for Poisson-Kingman mixture models

2015 · arXiv (Cornell University)

This paper concerns the introduction of a new Markov Chain Monte Carlo scheme for posterior sampling in Bayesian nonparametric mixture models with priors that belong to the general Poisson-Kingman class. We present a novel compact …

Neural Stochastic Differential Equations.

2019 · arXiv (Cornell University)

Deep neural networks whose parameters are distributed according to typical initialization schemes exhibit undesirable properties that can emerge as the number of layers increases. These issues include a vanishing dependency on the input and a …

Perfect Sampling of the Posterior in the Hierarchical Pitman–Yor Process

2021 · Bayesian Analysis

The predictive probabilities of the hierarchical Pitman-Yor process are approximated through Monte Carlo algorithms that exploits the Chinese Restaurant Franchise (CRF) representation. However, in order to simulate the posterior distribution of the hierarchical Pitman-Yor process, …