In this paper we propose a new approach for semi-supervised structured output learning. Our approach uses relaxed labeling on unlabeled data to deal with the combinatorial nature ...
Paramveer S. Dhillon, S. Sathiya Keerthi, Kedar Be...
This paper proposes a novel Bayesian approximation inference method for mixture modeling. Our key idea is to factorize marginal log-likelihood using a variational distribution ove...
Dynamic software updates can be used to fix bugs or add features to a running program without downtime. Essential for some applications and convenient for others, low-level dynami...
Gareth Stoyle, Michael W. Hicks, Gavin M. Bierman,...
An important element of understanding a software code base is to identify the repetitive patterns of code it contains and how these evolve over time. Some patterns are useful to t...
Traditionally, the topics of compiler construction and language processing have been taught as an elective course in Computer Science curricula. As such, students may graduate wit...