We have presented a neural framework for generalized topic models to enable rapid exploration of models with covariates, interactions, and customized regularizers. We take advantage of sampling-based variational inference to develop a general algo...

Overloading the Library Functions: It is not difficult to see that piecewise univariate functions can be implemented in our library.

We have proposed node-based learning of multiple Gaussian graphical models through the use of two convex formulations, perturbed-node joint graphical lasso and cohub node joint graphical lasso. These techniques are well-motivated by many real-worl...

We compare three generally-applicable strategies for translating out-of-vocabulary words, none of which rely on any language-specific resources or typological assumptions beyond the presence of subword units. Integrating these OOV translators into...

In addition to the questions stated in the previous sections, here we present three other fundamental directions that need to be explored to make causal analysis on multi-relational data robust and practical.