Due to advances in sensors, growing large and complex medical image data have the ability to visualize the pathological change in the cellular or even the molecular level or anatomical changes in tissues and organs. As a consequence, the medical images have the potential to enhance diagnosis of disease, prediction of clinical outcomes, characterization of disease progression, management of health care and development of treatments, but also pose great methodological and computational challenges for representation and selection of features in image cluster analysis. To address these challenges, we first extend one dimensional functional principal component analysis to the two dimensional functional principle component analyses (2DFPCA) to fully capture space variation of image signals. Image signals contain a large number of redundant and irrelevant features which provide no additional or no useful information for cluster analysis. Widely used methods for removing redundant and irrelevant features are sparse clustering algorithms using a lasso-type penalty to select the features. However, the accuracy of clustering using a lasso-type penalty depends on how to select penalty parameters and a threshold for selecting features. In practice, they are difficult to determine. Recently, randomized algorithms have received a great deal of attention in big data analysis. This paper presents a randomized algorithm for accurate feature selection in image cluster analysis. The proposed method is applied to ovarian and kidney cancer histology image data from the TCGA database. The results demonstrate that the randomized feature selection method coupled with functional principal component analysis substantially outperforms the current sparse clustering algorithms in image cluster analysis.

Restricted Boltzmann machines (RBMs) have proved to be a versatile tool for a wide variety of machine learning tasks and as a building block for deep architectures [12, 24, 28]. The original proposals mainly handle binary visible and hidden units. Whilst binary hidden units are broadly applicable as feature detectors, non-binary visible data requires different designs. Recent extensions to other data types result in type-dependent models: the Gaussian for continuous inputs [12], Beta for bounded continuous inputs [16], Poisson for count data [9], multinomial for unordered categories [25], and ordinal models for ordered categories [37, 35]. The Boltzmann distribution permits several types to be jointly modelled, thus making the RBM a good tool for multimodal and complex social survey analysis. The work of [20, 29, 40] combines continuous (e.g., visual and audio) and discrete modalities (e.g., words). The work of [34] extends the idea further to incorporate ordinal and rank data. However, there are conceptual drawbacks: First, conditioned on the hidden layer, they are still separate type-specific models; second, handling ordered categories and ranks is not natural; and third, specifying direct correlation between these types remains difficult. The main thesis of this paper is that many data types can be captured in one unified model.

Restricted Boltzmann machines (RBMs) [36, 9, 20] have recently attracted significant interest due to their versatility in a variety of unsupervised and supervised learning tasks [35, 18, 25], and in building deep architectures [14, 31]. A RBM is a bipartite undirected model that captures the generative process in which a data vector is generated from a binary hidden vector. The bipartite architecture enables very fast data encoding and sampling-based inference; and together with recent advances in learning procedures, we can now process massive data with large models [13, 37, 2]. This paper presents our contributions in developing RBM specifications as well as learning and inference procedures for multivariate ordinal data. This extends and consolidates the reach of RBMs to a wide range of user-generated domains - social responses, recommender systems, product/paper reviews, and expert assessments of health and ecosystems indicators.

Ranking over sets arise when users choose between groups of items. For example, a group may be of those movies deemed $5$ stars to them, or a customized tour package. It turns out, to model this data type properly, we need to investigate the general combinatorics problem of partitioning a set and ordering the subsets. Here we construct a probabilistic log-linear model over a set of ordered subsets. Inference in this combinatorial space is highly challenging: The space size approaches $(N!/2)6.93145^{N+1}$ as $N$ approaches infinity. We propose a \texttt{split-and-merge} Metropolis-Hastings procedure that can explore the state-space efficiently. For discovering hidden aspects in the data, we enrich the model with latent binary variables so that the posteriors can be efficiently evaluated. Finally, we evaluate the proposed model on large-scale collaborative filtering tasks and demonstrate that it is competitive against state-of-the-art methods.

Feature selection, identifying a subset of variables that are relevant for predicting a response, is an important and challenging component of many methods in statistics and machine learning. Feature selection is especially difficult and computationally intensive when the number of variables approaches or exceeds the number of samples, as is often the case for many genomic datasets. Here, we introduce a new approach -- the Bayesian Ising Approximation (BIA) -- to rapidly calculate posterior probabilities for feature relevance in L2 penalized linear regression. In the regime where the regression problem is strongly regularized by the prior, we show that computing the marginal posterior probabilities for features is equivalent to computing the magnetizations of an Ising model. Using a mean field approximation, we show it is possible to rapidly compute the feature selection path described by the posterior probabilities as a function of the L2 penalty. We present simulations and analytical results illustrating the accuracy of the BIA on some simple regression problems. Finally, we demonstrate the applicability of the BIA to high dimensional regression by analyzing a gene expression dataset with nearly 30,000 features.

Following the publication of an attack on genome-wide association studies (GWAS) data proposed by Homer et al., considerable attention has been given to developing methods for releasing GWAS data in a privacy-preserving way. Here, we develop an end-to-end differentially private method for solving regression problems with convex penalty functions and selecting the penalty parameters by cross-validation. In particular, we focus on penalized logistic regression with elastic-net regularization, a method widely used to in GWAS analyses to identify disease-causing genes. We show how a differentially private procedure for penalized logistic regression with elastic-net regularization can be applied to the analysis of GWAS data and evaluate our method's performance.

In many classification problems unlabelled data is abundant and a subset can be chosen for labelling. This defines the context of active learning (AL), where methods systematically select that subset, to improve a classifier by retraining. Given a classification problem, and a classifier trained on a small number of labelled examples, consider the selection of a single further example. This example will be labelled by the oracle and then used to retrain the classifier. This example selection raises a central question: given a fully specified stochastic description of the classification problem, which example is the optimal selection? If optimality is defined in terms of loss, this definition directly produces expected loss reduction (ELR), a central quantity whose maximum yields the optimal example selection. This work presents a new theoretical approach to AL, example quality, which defines optimal AL behaviour in terms of ELR. Once optimal AL behaviour is defined mathematically, reasoning about this abstraction provides insights into AL. In a theoretical context the optimal selection is compared to existing AL methods, showing that heuristics can make sub-optimal selections. Algorithms are constructed to estimate example quality directly. A large-scale experimental study shows these algorithms to be competitive with standard AL methods.

Matrix factorization (MF) has become a common approach to collaborative filtering, due to ease of implementation and scalability to large data sets. Two existing drawbacks of the basic model is that it does not incorporate side information on either users or items, and assumes a common variance for all users. We extend the work of constrained probabilistic matrix factorization by deriving the Gibbs updates for the side feature vectors for items (Salakhutdinov and Minh, 2008). We show that this Bayesian treatment to the constrained PMF model outperforms simple MAP estimation. We also consider extensions to heteroskedastic precision introduced in the literature (Lakshminarayanan, Bouchard, and Archambeau, 2011). We show that this tends result in overfitting for deterministic approximation algorithms (ex: Variational inference) when the observed entries in the user / item matrix are distributed in an non-uniform manner. In light of this, we propose a truncated precision model. Our experimental results suggest that this model tends to delay overfitting.

Non-negative blind source separation (non-negative BSS), which is also referred to as non-negative matrix factorization (NMF), is a very active field in domains as different as astrophysics, audio processing or biomedical signal processing. In this context, the efficient retrieval of the sources requires the use of signal priors such as sparsity. If NMF has now been well studied with sparse constraints in the direct domain, only very few algorithms can encompass non-negativity together with sparsity in a transformed domain since simultaneously dealing with two priors in two different domains is challenging. In this article, we show how a sparse NMF algorithm coined non-negative generalized morphological component analysis (nGMCA) can be extended to impose non-negativity in the direct domain along with sparsity in a transformed domain, with both analysis and synthesis formulations. To our knowledge, this work presents the first comparison of analysis and synthesis priors ---as well as their reweighted versions--- in the context of blind source separation. Comparisons with state-of-the-art NMF algorithms on realistic data show the efficiency as well as the robustness of the proposed algorithms.

In this paper we study lifted inference for the Weighted First-Order Model Counting problem (WFOMC), which counts the assignments that satisfy a given sentence in first-order logic (FOL); it has applications in Statistical Relational Learning (SRL) and Probabilistic Databases (PDB). We present several results. First, we describe a lifted inference algorithm that generalizes prior approaches in SRL and PDB. Second, we provide a novel dichotomy result for a non-trivial fragment of FO CNF sentences, showing that for each sentence the WFOMC problem is either in PTIME or #P-hard in the size of the input domain; we prove that, in the first case our algorithm solves the WFOMC problem in PTIME, and in the second case it fails. Third, we present several properties of the algorithm. Finally, we discuss limitations of lifted inference for symmetric probabilistic databases (where the weights of ground literals depend only on the relation name, and not on the constants of the domain), and prove the impossibility of a dichotomy result for the complexity of probabilistic inference for the entire language FOL.