Now, let's look at the fit on the training data and the corresponding confusion matrix. Our model performs only marginally better on the training data than our baseline model. We can see why this is the case: it predicts the average class (1) very often. Now we want to try this again with the test set. As you can see, we get a pretty much identical situation.

Several problems in modeling and control of stochastically-driven dynamical systems can be cast as regularized semi-definite programs. We examine two such representative problems and show that they can be formulated in a similar manner. The first, in statistical modeling, seeks to reconcile observed statistics by suitably and minimally perturbing prior dynamics. The second seeks to optimally select a subset of available sensors and actuators for control purposes. To address modeling and control of large-scale systems we develop a unified algorithmic framework using proximal methods. Our customized algorithms exploit problem structure and allow handling statistical modeling, as well as sensor and actuator selection, for substantially larger scales than what is amenable to current general-purpose solvers. We establish linear convergence of the proximal gradient algorithm, draw contrast between the proposed proximal algorithms and alternating direction method of multipliers, and provide examples that illustrate the merits and effectiveness of our framework. Index Terms Actuator selection, sensor selection, sparsity-promoting estimation and control, method of multipliers, nonsmooth convex optimization, proximal algorithms, regularization for design, semi-definite programming, structured covariances. I. INTRODUCTION Convex optimization has had tremendous impact on many disciplines, including system identification and control design [1]-[7]. The present paper focuses on two representative control problems, statistical control-oriented modeling and sensor/actuator selection, that are cast as convex programs.

As mobile devices become more and more popular, mobile gaming has emerged as a promising market with billion-dollar revenues. A variety of mobile game platforms and services have been developed around the world. A critical challenge for these platforms and services is to understand the churn behavior in mobile games, which usually involves churn at micro level (between an app and a specific user) and macro level (between an app and all its users). Accurate micro-level churn prediction and macro-level churn ranking will benefit many stakeholders such as game developers, advertisers, and platform operators. In this paper, we present the first large-scale churn analysis for mobile games that supports both micro-level churn prediction and macro-level churn ranking. For micro-level churn prediction, in view of the common limitations of the state-of-the-art methods built upon traditional machine learning models, we devise a novel semi-supervised and inductive embedding model that jointly learns the prediction function and the embedding function for user-app relationships. We model these two functions by deep neural networks with a unique edge embedding technique that is able to capture both contextual information and relationship dynamics. We also design a novel attributed random walk technique that takes into consideration both topological adjacency and attribute similarities. To address macro-level churn ranking, we propose to construct a relationship graph with estimated micro-level churn probabilities as edge weights and adapt link analysis algorithms on the graph. We devise a simple algorithm SimSum and adapt two more advanced algorithms PageRank and HITS. The performance of our solutions for the two-level churn analysis problems is evaluated on real-world data collected from the Samsung Game Launcher platform.

Statistical inference of analytically non-tractable posteriors is a difficult problem because of marginalization of correlated variables and stochastic methods such as MCMC and VI are commonly used. We argue that stochastic KL divergence minimization used by MCMC and VI is noisy, and we propose instead EL_2O, expectation optimization of L_2 distance squared between the approximate log posterior q and the un-normalized log posterior of p. When sampling from q the solutions agree with stochastic KL divergence minimization based VI in the large sample limit, however EL_2O method is free of sampling noise, has better optimization properties, and requires only as many sample evaluations as the number of parameters we are optimizing if q covers p. As a consequence, increasing the expressivity of q improves both the quality of results and the convergence rate, allowing EL_2O to approach exact inference. Use of automatic differentiation methods enables us to develop Hessian, gradient and gradient free versions of the method, which can determine M(M+2)/2+1, M+1 and 1 parameter(s) of q with a single sample, respectively. EL_2O provides a reliable estimate of the quality of the approximating posterior, and converges rapidly on full rank gaussian approximation for q and extensions beyond it, such as nonlinear transformations and gaussian mixtures. These can handle general posteriors, while still allowing fast analytic marginalizations. We test it on several examples, including a realistic 13 dimensional galaxy clustering analysis, showing that it is several orders of magnitude faster than MCMC, while giving smooth and accurate non-gaussian posteriors, often requiring a few to a few dozen of iterations only.

We present a novel notion of outlier, called the Concentration Free Outlier Factor, or CFOF. As a main contribution, we formalize the notion of concentration of outlier scores and theoretically prove that CFOF does not concentrate in the Euclidean space for any arbitrary large dimensionality. To the best of our knowledge, there are no other proposals of data analysis measures related to the Euclidean distance for which it has been provided theoretical evidence that they are immune to the concentration effect. We determine the closed form of the distribution of CFOF scores in arbitrarily large dimensionalities and show that the CFOF score of a point depends on its squared norm standard score and on the kurtosis of the data distribution, thus providing a clear and statistically founded characterization of this notion. Moreover, we leverage this closed form to provide evidence that the definition does not suffer of the hubness problem affecting other measures. We prove that the number of CFOF outliers coming from each cluster is proportional to cluster size and kurtosis, a property that we call semi-locality. We determine that semi-locality characterizes existing reverse nearest neighbor-based outlier definitions, thus clarifying the exact nature of their observed local behavior. We also formally prove that classical distance-based and density-based outliers concentrate both for bounded and unbounded sample sizes and for fixed and variable values of the neighborhood parameter. We introduce the fast-CFOF algorithm for detecting outliers in large high-dimensional dataset. The algorithm has linear cost, supports multi-resolution analysis, and is embarrassingly parallel. Experiments highlight that the technique is able to efficiently process huge datasets and to deal even with large values of the neighborhood parameter, to avoid concentration, and to obtain excellent accuracy.

Understanding the heat use of customers is crucial for effective district heating (DH) operations and management. Unfortunately, existing knowledge about customers and their heat load behaviors is quite scarce and very few studies have been focusing on this aspect. The deployment of smart meters offers a unique opportunity for researchers and DH utilities to analyze large-scale data and discover both typical, as well as atypical, patterns in the network. Heat load pattern discovery is a challenging task in DH systems, since a comprehensive analysis needs to involve many customers. Most of the past studies have relied on analysis of a small number of buildings, which are not shown to be picked as the representative examples. Therefore, the knowledge discovered in such studies is not enough to generalize for the entire network. In this work, we propose a data-driven approach that enables automatic discovery of heat load patterns in a complete district heating network. Our method clusters the buildings into different groups based on the characteristics of their load profiles, extracts the representative patterns for each of them, and detects abnormal profiles, i.e., the ones deviating from the expected behavior. We present the first comprehensive analysis of the heat load patterns by conducting a case study on all the buildings, in six customer categories, connected to two district heating networks in the south of Sweden. Our method has captured fifteen typical patterns among the heat load profiles of all buildings in our dataset. It shows that control strategies are not enough to explain the variability in the heat load behaviors. In conclusion, we demonstrate that the proposed approach has a great potential to develop knowledge about customers and their heat use habits in practice by automatically analyzing their typical and atypical profiles in large-scale.

A mutual information based upper bound on the generalization error of a supervised learning algorithm is derived in this paper. The bound is constructed in terms of the mutual information between each individual training sample and the output of the learning algorithm, which requires weaker conditions on the loss function, but provides a tighter characterization of the generalization error than existing studies. Examples are further provided to demonstrate that the bound derived in this paper is tighter, and has a broader range of applicability. Application to noisy and iterative algorithms, e.g., stochastic gradient Langevin dynamics (SGLD), is also studied, where the constructed bound provides a tighter characterization of the generalization error than existing results. I. INTRODUCTION Consider an instance space Z, a continuous hypothesis space W, and a nonnegative loss function l: W Z R Z drawn from an unknown distribution µ.

Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. However, this increased focus has led to considerable confusion about the notion of interpretability. In particular, it is unclear how the wide array of proposed interpretation methods are related, and what common concepts can be used to evaluate them. We aim to address these concerns by defining interpretability in the context of machine learning and introducing the Predictive, Descriptive, Relevant (PDR) framework for discussing interpretations. The PDR framework provides three overarching desiderata for evaluation: predictive accuracy, descriptive accuracy and relevancy, with relevancy judged relative to a human audience. Moreover, to help manage the deluge of interpretation methods, we introduce a categorization of existing techniques into model-based and post-hoc categories, with sub-groups including sparsity, modularity and simulatability. To demonstrate how practitioners can use the PDR framework to evaluate and understand interpretations, we provide numerous real-world examples. These examples highlight the often under-appreciated role played by human audiences in discussions of interpretability. Finally, based on our framework, we discuss limitations of existing methods and directions for future work. We hope that this work will provide a common vocabulary that will make it easier for both practitioners and researchers to discuss and choose from the full range of interpretation methods.

The field of probabilistic numerics (PN), loosely speaking, attempts to provide a statistical treatment of the errors and/or approximations that are made en route to the output of a deterministic numerical method, e.g. the approximation of an integral by quadrature, or the discretised solution of an ordinary or partial differential equation. This decade has seen a surge of activity in this field. In comparison with historical developments that can be traced back over more than a hundred years, the most recent developments are particularly interesting because they have been characterised by simultaneous input from multiple scientific disciplines: mathematics, statistics, machine learning, and computer science. The field has, therefore, advanced on a broad front, with contributions ranging from the building of overarching generaltheory to practical implementations in specific problems of interest. Over the same period of time, and because of increased interaction among researchers coming from different communities, the extent to which these developments were -- or were not -- presaged by twentieth-century researchers has also come to be better appreciated. Thus, the time appears to be ripe for an update of the 2014 Tübingen Manifesto on probabilistic numerics[Hennig, 2014, Osborne, 2014d,c,b,a] and the position paper[Hennig et al., 2015] to take account of the developments between 2014 and 2019, an improved awareness of the history of this field, and a clearer sense of its future directions. In this article, we aim to summarise some of the history of probabilistic perspectives on numerics (Section 2), to place more recent developments into context (Section 3), and to articulate a vision for future research in, and use of, probabilistic numerics (Section 4).

In the supervised high dimensional settings with a large number of variables and a low number of individuals, one objective is to select the relevant variables and thus to reduce the dimension. That subspace selection is often managed with supervised tools. However, some data can be missing, compromising the validity of the sub-space selection. We propose a Partial Least Square (PLS) based method, called Multi-block Data-Driven sparse PLS mdd-sPLS, allowing jointly variable selection and subspace estimation while training and testing missing data imputation through a new algorithm called Koh-Lanta. This method was challenged through simulations against existing methods such as mean imputation, nipals, softImpute and imputeMFA. In the context of supervised analysis of high dimensional data, the proposed method shows the lowest prediction error of the response variables. So far this is the only method combining data imputation and response variable prediction. The superiority of the supervised multi-block mdd-sPLS method increases with the intra-block and inter-block correlations. The application to a real data-set from a rVSV-ZEBOV Ebola vaccine trial revealed interesting and biologically relevant results. The method is implemented in a R-package available on the CRAN and a Python-package available on pypi.