
Stochastic Variational Inference
We develop stochastic variational inference, a scalable algorithm for ap...
read it

Empirical Bayes Model Averaging with Influential Observations: Tuning Zellner's g Prior for Predictive Robustness
We investigate the behavior of Bayesian model averaging (BMA) for the no...
read it

Hierarchical network models for structured exchangeable interaction processes
Network data often arises via a series of structured interactions among ...
read it

Robust Probabilistic Modeling with Bayesian Data Reweighting
Probabilistic models analyze data by relying on a set of assumptions. Da...
read it

A Note on the Accuracy of Variational Bayes in State Space Models: Inference and Prediction
Using theoretical and numerical results, we document the accuracy of com...
read it

Deconvolution of dust mixtures by latent Dirichlet allocation in forensic science
Dust particles recovered from the soles of shoes may be indicative of th...
read it

Streaming Variational Bayes
We present SDABayes, a framework for (S)treaming, (D)istributed, (A)syn...
read it
Population Empirical Bayes
Bayesian predictive inference analyzes a dataset to make predictions about new observations. When a model does not match the data, predictive accuracy suffers. We develop population empirical Bayes (POPEB), a hierarchical framework that explicitly models the empirical population distribution as part of Bayesian analysis. We introduce a new concept, the latent dataset, as a hierarchical variable and set the empirical population as its prior. This leads to a new predictive density that mitigates model mismatch. We efficiently apply this method to complex models by proposing a stochastic variational inference algorithm, called bumping variational inference (BUMPVI). We demonstrate improved predictive accuracy over classical Bayesian inference in three models: a linear regression model of health data, a Bayesian mixture model of natural images, and a latent Dirichlet allocation topic model of scientific documents.
READ FULL TEXT
Comments
There are no comments yet.