Data-flow analysis is a common technique to gather program information for use in transformations such as register allocation, dead-code elimination, common subexpression elimina...
Hidden Markov Models (HMMs) are important tools for modeling sequence data. However, they are restricted to discrete latent states, and are largely restricted to Gaussian and disc...
Le Song, Sajid M. Siddiqi, Geoffrey J. Gordon, Ale...
Unsupervised sequence learning is important to many applications. A learner is presented with unlabeled sequential data, and must discover sequential patterns that characterize th...
Multi-task learning (MTL) aims to improve the performance of multiple related tasks by exploiting the intrinsic relationships among them. Recently, multi-task feature learning alg...
Many real world learning problems are best characterized by an interaction of multiple independent causes or factors. Discovering such causal structure from the data is the focus ...