DLVHEX System google
The DLVHEX system implements the HEX-semantics, which integrates answer set programming (ASP) with arbitrary external sources. Since its first release ten years ago, significant advancements were achieved. Most importantly, the exploitation of properties of external sources led to efficiency improvements and flexibility enhancements of the language, and technical improvements on the system side increased user’s convenience. In this paper, we present the current status of the system and point out the most important recent enhancements over early versions. While existing literature focuses on theoretical aspects and specific components, a bird’s eye view of the overall system is missing. In order to promote the system for real-world applications, we further present applications which were already successfully realized on top of DLVHEX. This paper is under consideration for acceptance in Theory and Practice of Logic Programming. …

Conway-Maxwell Poisson (CMP) google
Count data are a popular outcome in many empirical studies, especially as big data has become available on human and social behavior. The Conway-Maxwell Poisson (CMP) distribution is popularly used for modeling count data due to its ability to handle both overdispersed and underdispersed data. Yet, current methods for estimating CMP regression models are not efficient, especially with high-dimensional data. Extant methods use either nonlinear optimization or MCMC methods. We propose a flexible estimation framework for CMP regression based on iterative reweighed least squares (IRLS). Because CMP belongs to the exponential family, convergence is guaranteed and is more efficient. We also extend this framework to allow estimation for additive models with smoothing splines. We illustrate the usefulness of this approach through simulation study and application to real data on speed dating. …

Autoencoded Variational Inference For Topic Model (AVITM) google
Topic models are one of the most popular methods for learning representations of text, but a major challenge is that any change to the topic model requires mathematically deriving a new inference algorithm. A promising approach to address this problem is autoencoding variational Bayes (AEVB), but it has proven difficult to apply to topic models in practice. We present what is to our knowledge the first effective AEVB based inference method for latent Dirichlet allocation (LDA), which we call Autoencoded Variational Inference For Topic Model (AVITM). This model tackles the problems caused for AEVB by the Dirichlet prior and by component collapsing. We find that AVITM matches traditional methods in accuracy with much better inference time. Indeed, because of the inference network, we find that it is unnecessary to pay the computational cost of running variational optimization on test data. Because AVITM is black box, it is readily applied to new topic models. As a dramatic illustration of this, we present a new topic model called ProdLDA, that replaces the mixture model in LDA with a product of experts. By changing only one line of code from LDA, we find that ProdLDA yields much more interpretable topics, even if LDA is trained via collapsed Gibbs sampling. …

Advertisements