Causal mediation analysis (CMA) is a powerful method to dissect the tota...
Unsupervised domain adaptation (UDA) is a technique used to transfer
kno...
Over the past few decades, a number of methods have been proposed for ca...
It is challenging to guide neural network (NN) learning with prior knowl...
Observational studies are regarded as economic alternatives to randomize...
Deep autoencoders are often extended with a supervised or adversarial lo...
Many causal inference approaches have focused on identifying an individu...
Probabilistic generative models are attractive for scientific modeling
b...
Factor models are routinely used for dimensionality reduction in modelin...
Effective decision making requires understanding the uncertainty inheren...
Textual network embedding aims to learn low-dimensional representations ...
Despite the widespread usage of machine learning throughout organization...
In this work we propose a new task called Story Visualization. Given a
m...
Generating videos from text has proven to be a significant challenge for...
We introduce a novel stochastic version of the non-reversible, rejection...
Partition functions of probability distributions are important quantitie...
Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayes...
Effective training of deep neural networks suffers from two main issues....
Neuroprosthetic brain-computer interfaces function via an algorithm whic...
Deep dynamic generative models are developed to learn sequential depende...