We present an automatic classification method for astronomical catalogs with missing data. We use Bayesian networks, a probabilistic graphical model, that allows us to perform inference to pre- dict missing values given observed data and dependency relationships between variables. To learn a Bayesian network from incomplete data, we use an iterative algorithm that utilises sampling methods and expectation maximization to estimate the distributions and probabilistic dependencies of variables from data with missing values. To test our model we use three catalogs with missing data (SAGE, 2MASS and UBVI) and one complete catalog (MACHO). We examine how classification accuracy changes when information from missing data catalogs is included, how our method compares to traditional missing data approaches and at what computational cost. Integrating these catalogs with missing data we find that classification of variable objects improves by few percent and by 15% for quasar detection while keeping the computational cost the same.

This report describes the suicidality prediction models created under the DARPA DCAPS program in association with the Durkheim Project [http://durkheimproject.org/]. The models were built primarily from unstructured text (free-format clinician notes) for several hundred patient records obtained from the Veterans Health Administration (VHA). The models were constructed using a genetic programming algorithm applied to bag-of-words and bag-of-phrases datasets. The influence of additional structured data was explored but was found to be minor. Given the small dataset size, classification between cohorts was high fidelity (98%). Cross-validation suggests these models are reasonably predictive, with an accuracy of 50% to 69% on five rotating folds, with ensemble averages of 58% to 67%. One particularly noteworthy result is that word-pairs can dramatically improve classification accuracy; but this is the case only when one of the words in the pair is already known to have a high predictive value. By contrast, the set of all possible word-pairs does not improve on a simple bag-of-words model.

Combining information from different sources is a common way to improve classification accuracy in Brain-Computer Interfacing (BCI). For instance, in small sample settings it is useful to integrate data from other subjects or sessions in order to improve the estimation quality of the spatial filters or the classifier. Since data from different subjects may show large variability, it is crucial to weight the contributions according to importance. Many multi-subject learning algorithms determine the optimal weighting in a separate step by using heuristics, however, without ensuring that the selected weights are optimal with respect to classification. In this work we apply Multiple Kernel Learning (MKL) to this problem. MKL has been widely used for feature fusion in computer vision and allows to simultaneously learn the classifier and the optimal weighting. We compare the MKL method to two baseline approaches and investigate the reasons for performance improvement.

In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical use of the confusion matrix of a classifier as an error measure; this puts our contribution in the line of work aiming at dealing with performance measure that are richer than mere scalar criterion such as the misclassification rate. Thanks to very recent and beautiful results on matrix concentration inequalities, we derive two bounds showing that the true confusion risk of the Gibbs classifier is upper-bounded by its empirical risk plus a term depending on the number of training examples in each class. To the best of our knowledge, this is the first PAC-Bayes bounds based on confusion matrices.

We propose a voted dual averaging method for online classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA) method, but only on the subsequence of training examples where a classification error is made. We derive a bound on the number of mistakes made by this method on the training set, as well as its generalization error rate. We also introduce the concept of relative strength of regularization, and show how it affects the mistake bound and generalization performance. We experimented with the method using $\ell_1$ regularization on a large-scale natural language processing task, and obtained state-of-the-art classification performance with fairly sparse models.

In the era of big data, a large amount of noisy and incomplete data can be collected from multiple sources for prediction tasks. Combining multiple models or data sources helps to counteract the effects of low data quality and the bias of any single model or data source, and thus can improve the robustness and the performance of predictive models. Out of privacy, storage and bandwidth considerations, in certain circumstances one has to combine the predictions from multiple models or data sources to obtain the final predictions without accessing the raw data. Consensus-based prediction combination algorithms are effective for such situations. However, current research on prediction combination focuses on the single label setting, where an instance can have one and only one label. Nonetheless, data nowadays are usually multilabeled, such that more than one label have to be predicted at the same time. Direct applications of existing prediction combination methods to multilabel settings can lead to degenerated performance. In this paper, we address the challenges of combining predictions from multiple multilabel classifiers and propose two novel algorithms, MLCM-r (MultiLabel Consensus Maximization for ranking) and MLCM-a (MLCM for microAUC). These algorithms can capture label correlations that are common in multilabel classifications, and optimize corresponding performance metrics. Experimental results on popular multilabel classification tasks verify the theoretical analysis and effectiveness of the proposed methods.

Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game researches. Among a variety of PCG techniques, search-based approaches overwhelmingly dominate PCG development at present. While SBPCG leads to promising results and successful applications, it poses a number of challenges ranging from representation to evaluation of the content being generated. In this paper, we present an alternative yet generic PCG framework, named learning-based procedure content generation (LBPCG), to provide potential solutions to several challenging problems in existing PCG techniques. By exploring and exploiting information gained in game development and public beta test via data-driven learning, our framework can generate robust content adaptable to end-user or target players on-line with minimal interruption to their experience. Furthermore, we develop enabling techniques to implement the various models required in our framework. For a proof of concept, we have developed a prototype based on the classic open source first-person shooter game, Quake. Simulation results suggest that our framework is promising in generating quality content.

We consider constraint-based methods for causal structure learning, such as the PC-, FCI-, RFCI- and CCD- algorithms (Spirtes et al. (2000, 1993), Richardson (1996), Colombo et al. (2012), Claassen et al. (2013)). The first step of all these algorithms consists of the PC-algorithm. This algorithm is known to be order-dependent, in the sense that the output can depend on the order in which the variables are given. This order-dependence is a minor issue in low-dimensional settings. We show, however, that it can be very pronounced in high-dimensional settings, where it can lead to highly variable results. We propose several modifications of the PC-algorithm (and hence also of the other algorithms) that remove part or all of this order-dependence. All proposed modifications are consistent in high-dimensional settings under the same conditions as their original counterparts. We compare the PC-, FCI-, and RFCI-algorithms and their modifications in simulation studies and on a yeast gene expression data set. We show that our modifications yield similar performance in low-dimensional settings and improved performance in high-dimensional settings. All software is implemented in the R-package pcalg.

Joint sparsity regularization in multi-task learning has attracted much attention in recent years. The traditional convex formulation employs the group Lasso relaxation to achieve joint sparsity across tasks. Although this approach leads to a simple convex formulation, it suffers from several issues due to the looseness of the relaxation. To remedy this problem, we view jointly sparse multi-task learning as a specialized random effects model, and derive a convex relaxation approach that involves two steps. The first step learns the covariance matrix of the coefficients using a convex formulation which we refer to as sparse covariance coding; the second step solves a ridge regression problem with a sparse quadratic regularizer based on the covariance matrix obtained in the first step. It is shown that this approach produces an asymptotically optimal quadratic regularizer in the mul-titask learning setting when the number of tasks approaches infinity. Experimental results demonstrate that the convex formulation obtained via the proposed model significantly outperforms group Lasso (and related multistage formulations).

The clinical pathology of neurological diseases and the imaging of the human brain are two areas of research that have largely developed along independent lines. It is only in the past few years that the usefulness of noninvasive imaging measurements of the human brain to the diagnosis and early prediction of neurological diseases been widely recognised (Albert et al., 2011; Sperling et al., 2011; Gray et al., 2013). In Alzheimer's Disease (AD), for instance, clinical guidance on the diagnosis of this most common of neurological degenerative disorders has recently been updated to incorporate neuroimaging markers alongside standard cognitive and behavioural tests (Albert et al., 2011; Sperling et al., 2011). The key to the improved characterisation of AD lies in the quantitative nature of the imaging measurements compared to the relatively subjective and imprecise nature of traditional clinical assessments. Imaging biomarkers of cerebral atrophy and of loss of connectivity between key regions in the brain are believed to be reliable indicators of AD and are particularly useful at early disease stages when standard cognitive assessments can be inconclusive. The utility of imaging phenotypes extends beyond diagnosis and prediction to the search for the underlying genetic factors behind neurological disorders (Stein et al., 2010). This comparatively more recent use of neuroimaging measurements in place of case-control labels in genetic association studies defines the emerging field of imaging genetics. The central premise here is that, should they exist, genetic associations to intermediate brain structure and brain function phenotypes are stronger than those with the categorical clinical disease statuses further down the etiological chain (Glahn et al., 2007). Again, the example of AD serves as a good illustration.