Latent Dirichlet Allocation (LDA) is a topic model widely used in natural language processing and machine learning. Most approaches to training the model rely on iterative algorithms, which makes it difficult to run LDA on big data sets that are best analyzed in parallel and distributed computational environments. Indeed, current approaches to parallel inference either don't converge to the correct posterior or require storage of large dense matrices in memory. We present a novel sampler that overcomes both problems, and we show that this sampler is faster, both empirically and theoretically, than previous Gibbs samplers for LDA. We do so by employing a novel Pólya-Urn-based approximation in the sparse partially collapsed sampler for LDA. We prove that the approximation error vanishes with data size, making our algorithm asymptotically exact, a property of importance for large-scale topic models. In addition, we show, via an explicit example, that - contrary to popular belief in the topic modeling literature - partially collapsed samplers can be more efficient than fully collapsed samplers. We conclude by comparing the performance of our algorithm with that of other approaches on well-known corpora. Keywords: Bayesian inference, Big Data, computational complexity, Gibbs sampling, Latent Dirichlet Allocation, Markov Chain Monte Carlo, natural language processing, parallel and distributed systems, topic models.

In this article, a semi-supervised classification algorithm implementation will be described using Markov Chains and Random Walks. We have the following 2D circles dataset (with 1000 points) with only 2 points labeled (as shown in the figure, colored red and blue respectively, for all others the labels are unknown, indicated by the color black). Now the task is to predict the labels of the other (unlabeled) points. From each of the unlabeled points (Markov states) a random walk with Markov transition matrix (computed from the row-stochastic kernelized distance matrix) will be started that will end in one labeled state, which will be an absorbing state in the Markov Chain. This problem was discussed as an application of Markov Chain in a lecture from the edX course ColumbiaX: CSMM.102x

You're refining your training set, and maybe you've even tried stuff out using Naive Bayes. But now you're feeling confident in your dataset, and want to take it one step further. Enter Support Vector Machines (SVM): a fast and dependable classification algorithm that performs very well with a limited amount of data. Perhaps you have dug a bit deeper, and ran into terms like linearly separable, kernel trick and kernel functions. The idea behind the SVM algorithm is simple, and applying it to natural language classification doesn't require most of the complicated stuff.

It is no doubt that the sub-field of machine learning / artificial intelligence has increasingly gained more popularity in the past couple of years. As Big Data is the hottest trend in the tech industry at the moment, machine learning is incredibly powerful to make predictions or calculated suggestions based on large amounts of data. Some of the most common examples of machine learning are Netflix's algorithms to make movie suggestions based on movies you have watched in the past or Amazon's algorithms that recommend books based on books you have bought before. So if you want to learn more about machine learning, how do you start? For me, my first introduction is when I took an Artificial Intelligence class when I was studying abroad in Copenhagen.

Learning Bayesian networks from raw data can help provide insights into the relationships between variables. While real data often contains a mixture of discrete and continuous-valued variables, many Bayesian network structure learning algorithms assume all random variables are discrete. Thus, continuous variables are often discretized when learning a Bayesian network. However, the choice of discretization policy has significant impact on the accuracy, speed, and interpretability of the resulting models. This paper introduces a principled Bayesian discretization method for continuous variables in Bayesian networks with quadratic complexity instead of the cubic complexity of other standard techniques. Empirical demonstrations show that the proposed method is superior to the established minimum description length algorithm. In addition, this paper shows how to incorporate existing methods into the structure learning process to discretize all continuous variables and simultaneously learn Bayesian network structures.

We consider the problem of recovering a function input of a differential equation formulated on an unknown domain $M$. We assume to have access to a discrete domain $M_n=\{x_1, \dots, x_n\} \subset M$, and to noisy measurements of the output solution at $p\le n$ of those points. We introduce a graph-based Bayesian inverse problem, and show that the graph-posterior measures over functions in $M_n$ converge, in the large $n$ limit, to a posterior over functions in $M$ that solves a Bayesian inverse problem with known domain. The proofs rely on the variational formulation of the Bayesian update, and on a new topology for the study of convergence of measures over functions on point clouds to a measure over functions on the continuum. Our framework, techniques, and results may serve to lay the foundations of robust uncertainty quantification of graph-based tasks in machine learning. The ideas are presented in the concrete setting of recovering the initial condition of the heat equation on an unknown manifold.

Feature subset selection arises in many high-dimensional applications of statistics, such as compressed sensing and genomics. The $\ell_0$ penalty is ideal for this task, the caveat being it requires the NP-hard combinatorial evaluation of all models. A recent area of considerable interest is to develop efficient algorithms to fit models with a non-convex $\ell_\gamma$ penalty for $\gamma\in (0,1)$, which results in sparser models than the convex $\ell_1$ or lasso penalty, but is harder to fit. We propose an alternative, termed the horseshoe regularization penalty for feature subset selection, and demonstrate its theoretical and computational advantages. The distinguishing feature from existing non-convex optimization approaches is a full probabilistic representation of the penalty as the negative of the logarithm of a suitable prior, which in turn enables efficient expectation-maximization and local linear approximation algorithms for optimization and MCMC for uncertainty quantification. In synthetic and real data, the resulting algorithms provide better statistical performance, and the computation requires a fraction of time of state-of-the-art non-convex solvers.

This article was written by Natasha Latysheva. Here we publish a short version, with references to full source code in the original article. In machine learning, you may often wish to build predictors that allows to classify things into categories based on some set of associated values. For example, it is possible to provide a diagnosis to a patient based on data from previous patients. Many algorithms have been developed for automated classification, and common ones include random forests, support vector machines, Naïve Bayes classifiers, and many types of neural networks.

Bayesian Statistics continues to remain incomprehensible in the ignited minds of many analysts. Being amazed by the incredible power of machine learning, a lot of us have become unfaithful to statistics. Our focus has narrowed down to exploring machine learning. We fail to understand that machine learning is only one way to solve real world problems. In several situations, it does not help us solve business problems, even though there is data involved in these problems. To say the least, knowledge of statistics will allow you to work on complex analytical problems, irrespective of the size of data. In 1770s, Thomas Bayes introduced'Bayes Theorem'.

An ensemble of models (EM), where each model is constructed on a diverse subset of feature variables, is proposed to rank rare class items ahead of majority class items in a highly unbalanced two class problem. The proposed ensemble relies on an algorithm to group the feature variables into subsets where the variables in a subset work better together in a model and the variables in different subsets work better in separate models. The strength of the EM depends on the algorithm's ability to identify strong and diverse subsets of feature variables. A second phase of ensembling is achieved by aggregating several EMs each optimized on a diverse evaluation metric. The resulting ensemble is called ensemble of models and metrics (EMM). Here, the diverse/complementary evaluation metrics ensure increased diversity among EMs to aggregate. The ensembles are applied to the protein homology data, downloaded from the 2004 KDD cup competition website, to rank proteins in such a way that the rare homologous proteins are found ahead of the majority non-homologous proteins. The ensembles are constructed using feature variables which are various scores from sequence alignments of amino acids in a candidate protein and three dimensional descriptions of a native protein representing functional and structural similarity of proteins. While prediction performances of the EMs are better than the contemporary state-of-the-art ensembles and competitive to the winning procedures of the $2004$ KDD cup competition, the performances of the EMM are found on the top of all. In this application, we have two diverse EMs constructed on two complementary evaluation metrics average precision and rank last, where the former is robust against ranking close homologs and the latter is robust against ranking distant homologs. The advantage of using EMM is that it is robust against both close and distant homologs.