Seminars

Interpretable machine learning has been widely deployed for scientific discoveries and decision-making, while its reliability hinges on the critical role…

In this talk, I will first present a Bayesian semiparametric method of jointly estimating the density function and the tail…

Large crossed mixed effects models with imbalanced structures and missing data pose major computational challenges for standard Bayesian posterior sampling…

Classical machine learning framework focuses on single-stage learning, where we directly estimate the target prediction function from training data sets….

A growing number of nanomedicines have been developed for drug delivery via injection into the bloodstream. These nanocarriers transport drug…

In statistical and probabilistic models, “mean-field” behavior arises when the aggregate effect of many variables is well-approximated by an average…

In recent years, graphs have become one of the most powerful abstractions for complex data, including brain networks, knowledge graphs,…

Tensor data, which exhibits more sophisticated structures than matrix data and brings unique statistical and computational challenges, has attracted a…

In statistical and probabilistic models, “mean-field” behavior arises when the aggregate effect of many variables is well-approximated by an average…

Statistical inference from high-dimensional data with low-dimensional structures has recently attracted a lot of attention. In machine learning, deep generative…