This paper considers a portfolio trading strategy formulated by algorithms in the field of machine learning. The profitability of the strategy is measured by the algorithm's capability to consistently and accurately identify stock indices with positive or negative returns, and to generate a preferred portfolio allocation on the basis of a learned model. Stocks are characterized by time series data sets consisting of technical variables that reflect market conditions in a previous time interval, which are utilized produce binary classification decisions in subsequent intervals. The learned model is constructed as a committee of random forest classifiers, a non-linear support vector machine classifier, a relevance vector machine classifier, and a constituent ensemble of k-nearest neighbors classifiers. The Global Industry Classification Standard (GICS) is used to explore the ensemble model's efficacy within the context of various fields of investment including Energy, Materials, Financials, and Information Technology. Data from 2006 to 2012, inclusive, are considered, which are chosen for providing a range of market circumstances for evaluating the model. The model is observed to achieve an accuracy of approximately 70% when predicting stock price returns three months in advance.

One of the major challenges to building intelligent educational software is determining what kinds of feedback to give learners. Useful feedback makes use of models of domain-specific knowledge, especially models that are commonly held by potential students. To empirically determine what these models are, student data can be clustered to reveal common misconceptions or common problem-solving strategies. This article describes how analogical retrieval and generalization can be used to cluster automatically analyzed hand-drawn sketches incorporating both spatial and conceptual information. We use this approach to cluster a corpus of hand-drawn student sketches to discover common answers. Common answer clusters can be used for the design of targeted feedback and for assessment.

This article describes GRADE, a statistical machine learning system developed to support the work of the graduate admissions committee at the University of Texas at Austin Department of Computer Science (UTCS). In recent years, the number of applications to the UTCS PhD program has become too large to manage with a traditional review process. GRADE uses historical admissions data to predict how likely the committee is to admit each new applicant. It reports each prediction as a score similar to those used by human reviewers, and accompanies each by an explanation of what applicant features most influenced its prediction. GRADE makes the review process more efficient by enabling reviewers to spend most of their time on applicants near the decision boundary and by focusing their attention on parts of each applicant’s file that matter the most. An evaluation over two seasons of PhD admissions indicates that the system leads to dramatic time savings, reducing the total time spent on reviews by at least 74 percent.

Principal component analysis (PCA) is a mainstay of modern data analysis - a black box that is widely used but (sometimes) poorly understood. The goal of this paper is to dispel the magic behind this black box. This manuscript focuses on building a solid intuition for how and why principal component analysis works. This manuscript crystallizes this knowledge by deriving from simple intuitions, the mathematics behind PCA. This tutorial does not shy away from explaining the ideas informally, nor does it shy away from the mathematics. The hope is that by addressing both aspects, readers of all levels will be able to gain a better understanding of PCA as well as the when, the how and the why of applying this technique.

A main challenge of data-driven sciences is how to make maximal use of the progressively expanding databases of experimental datasets in order to keep research cumulative. We introduce the idea of a modeling-based dataset retrieval engine designed for relating a researcher's experimental dataset to earlier work in the field. The search is (i) data-driven to enable new findings, going beyond the state of the art of keyword searches in annotations, (ii) modeling-driven, to both include biological knowledge and insights learned from data, and (iii) scalable, as it is accomplished without building one unified grand model of all data. Assuming each dataset has been modeled beforehand, by the researchers or by database managers, we apply a rapidly computable and optimizable combination model to decompose a new dataset into contributions from earlier relevant models. By using the data-driven decomposition we identify a network of interrelated datasets from a large annotated human gene expression atlas. While tissue type and disease were major driving forces for determining relevant datasets, the found relationships were richer and the model-based search was more accurate than keyword search; it moreover recovered biologically meaningful relationships that are not straightforwardly visible from annotations, for instance, between cells in different developmental stages such as thymocytes and T-cells. Data-driven links and citations matched to a large extent; the data-driven links even uncovered corrections to the publication data, as two of the most linked datasets were not highly cited and turned out to have wrong publication entries in the database.

Associating genetic markers with a multidimensional phenotype is an important yet challenging problem. In this work, we establish the equivalence between two popular methods: kernel-machine regression (KMR), and kernel distance covariance (KDC). KMR is a semiparametric regression frameworks that models the covariate effects parametrically, while the genetic markers are considered non-parametrically. KDC represents a class of methods that includes distance covariance (DC) and Hilbert-Schmidt Independence Criterion (HSIC), which are nonparametric tests of independence. We show the equivalence between the score test of KMR and the KDC statistic under certain conditions. This result leads to a novel generalization of the KDC test that incorporates the covariates. Our contributions are three-fold: (1) establishing the equivalence between KMR and KDC; (2) showing that the principles of kernel machine regression can be applied to the interpretation of KDC; (3) the development of a broader class of KDC statistics, that the members are the quantities of different kernels. We demonstrate the proposals using simulation studies. Data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) is used to explore the association between the genetic variants on gene \emph{FLJ16124} and phenotypes represented in 3D structural brain MR images adjusting for age and gender. The results suggest that SNPs of \emph{FLJ16124} exhibit strong pairwise interaction effects that are correlated to the changes of brain region volumes.

Recent research has shown that a single arbitrarily efficient solver can be significantly outperformed by a portfolio of possibly slower on-average solvers. The solver selection is usually done by means of (un)supervised learning techniques which exploit features extracted from the problem specification. In this paper we present an useful and flexible framework that is able to extract an extensive set of features from a Constraint (Satisfaction/Optimization) Problem defined in possibly different modeling languages: MiniZinc, FlatZinc or XCSP. We also report some empirical results showing that the performances that can be obtained using these features are effective and competitive with state of the art CSP portfolio techniques.

We describe Venture, an interactive virtual machine for probabilistic programming that aims to be sufficiently expressive, extensible, and efficient for general-purpose use. Like Church, probabilistic models and inference problems in Venture are specified via a Turing-complete, higher-order probabilistic language descended from Lisp. Unlike Church, Venture also provides a compositional language for custom inference strategies built out of scalable exact and approximate techniques. We also describe four key aspects of Venture's implementation that build on ideas from probabilistic graphical models. First, we describe the stochastic procedure interface (SPI) that specifies and encapsulates primitive random variables. The SPI supports custom control flow, higher-order probabilistic procedures, partially exchangeable sequences and ``likelihood-free'' stochastic simulators. It also supports external models that do inference over latent variables hidden from Venture. Second, we describe probabilistic execution traces (PETs), which represent execution histories of Venture programs. PETs capture conditional dependencies, existential dependencies and exchangeable coupling. Third, we describe partitions of execution histories called scaffolds that factor global inference problems into coherent sub-problems. Finally, we describe a family of stochastic regeneration algorithms for efficiently modifying PET fragments contained within scaffolds. Stochastic regeneration linear runtime scaling in cases where many previous approaches scaled quadratically. We show how to use stochastic regeneration and the SPI to implement general-purpose inference strategies such as Metropolis-Hastings, Gibbs sampling, and blocked proposals based on particle Markov chain Monte Carlo and mean-field variational inference techniques.

Sparse clustering, which aims to find a proper partition of an extremely high-dimensional data set with redundant noise features, has been attracted more and more interests in recent years. The existing studies commonly solve the problem in a framework of maximizing the weighted feature contributions subject to a $\ell_2/\ell_1$ penalty. Nevertheless, this framework has two serious drawbacks: One is that the solution of the framework unavoidably involves a considerable portion of redundant noise features in many situations, and the other is that the framework neither offers intuitive explanations on why this framework can select relevant features nor leads to any theoretical guarantee for feature selection consistency. In this article, we attempt to overcome those drawbacks through developing a new sparse clustering framework which uses a $\ell_{\infty}/\ell_0$ penalty. First, we introduce new concepts on optimal partitions and noise features for the high-dimensional data clustering problems, based on which the previously known framework can be intuitively explained in principle. Then, we apply the suggested $\ell_{\infty}/\ell_0$ framework to formulate a new sparse k-means model with the $\ell_{\infty}/\ell_0$ penalty ($\ell_0$-k-means for short). We propose an efficient iterative algorithm for solving the $\ell_0$-k-means. To deeply understand the behavior of $\ell_0$-k-means, we prove that the solution yielded by the $\ell_0$-k-means algorithm has feature selection consistency whenever the data matrix is generated from a high-dimensional Gaussian mixture model. Finally, we provide experiments with both synthetic data and the Allen Developing Mouse Brain Atlas data to support that the proposed $\ell_0$-k-means exhibits better noise feature detection capacity over the previously known sparse k-means with the $\ell_2/\ell_1$ penalty ($\ell_1$-k-means for short).

We propose a novel method for maximum likelihood-based parameter inference in nonlinear and/or non-Gaussian state space models. The method is an iterative procedure with three steps. At each iteration a particle filter is used to estimate the value of the log-likelihood function at the current parameter iterate. Using these log-likelihood estimates, a surrogate objective function is created by utilizing a Gaussian process model. Finally, we use a heuristic procedure to obtain a revised parameter iterate, providing an automatic trade-off between exploration and exploitation of the surrogate model. The method is profiled on two state space models with good performance both considering accuracy and computational cost.