In this paper, we study CPU utilization time patterns of several MapReduce applications. After extracting running patterns of several applications, they are saved in a reference database to be later used to tweak system parameters to efficiently execute unknown applications in future. To achieve this goal, CPU utilization patterns of new applications are compared with the already known ones in the reference database to find/predict their most probable execution patterns. Because of different patterns lengths, the Dynamic Time Warping (DTW) is utilized for such comparison; a correlation analysis is then applied to DTWs outcomes to produce feasible similarity patterns. Three real applications (WordCount, Exim Mainlog parsing and Terasort) are used to evaluate our hypothesis in tweaking system parameters in executing similar applications. Results were very promising and showed effectiveness of our approach on pseudo-distributed MapReduce platforms.

The modeling of cascade processes in multi-agent systems in the form of complex networks has in recent years become an important topic of study due to its many applications: the adoption of commercial products, spread of disease, the diffusion of an idea, etc. In this paper, we begin by identifying a desiderata of seven properties that a framework for modeling such processes should satisfy: the ability to represent attributes of both nodes and edges, an explicit representation of time, the ability to represent non-Markovian temporal relationships, representation of uncertain information, the ability to represent competing cascades, allowance of non-monotonic diffusion, and computational tractability. We then present the MANCaLog language, a formalism based on logic programming that satisfies all these desiderata, and focus on algorithms for finding minimal models (from which the outcome of cascades can be obtained) as well as how this formalism can be applied in real world scenarios. We are not aware of any other formalism in the literature that meets all of the above requirements.

Sparse feature selection has been demonstrated to be effective in handling high-dimensional data. While promising, most of the existing works use convex methods, which may be suboptimal in terms of the accuracy of feature selection and parameter estimation. In this paper, we expand a nonconvex paradigm to sparse group feature selection, which is motivated by applications that require identifying the underlying group structure and performing feature selection simultaneously. The main contributions of this article are twofold: (1) statistically, we introduce a nonconvex sparse group feature selection model which can reconstruct the oracle estimator. Therefore, consistent feature selection and parameter estimation can be achieved; (2) computationally, we propose an efficient algorithm that is applicable to large-scale problems. Numerical results suggest that the proposed nonconvex method compares favorably against its competitors on synthetic data and real-world applications, thus achieving desired goal of delivering high performance.

Ubiquitous information access becomes more and more important nowadays and research is aimed at making it adapted to users. Our work consists in applying machine learning techniques in order to adapt the information access provided by ubiquitous systems to users when the system only knows the user social group, without knowing anything about the user interest. The adaptation procedures associate actions to perceived situations of the user. Associations are based on feedback given by the user as a reaction to the behavior of the system. Our method brings a solution to some of the problems concerning the acceptance of the system by users when applying machine learning techniques to systems at the beginning of the interaction between the system and the user.

Financial portfolio optimization is a widely studied problem in mathematics, statistics, financial and computational literature. It adheres to determining an optimal combination of weights associated with financial assets held in a portfolio. In practice, it faces challenges by virtue of varying math. formulations, parameters, business constraints and complex financial instruments. Empirical nature of data is no longer one-sided; thereby reflecting upside and downside trends with repeated yet unidentifiable cyclic behaviours potentially caused due to high frequency volatile movements in asset trades. Portfolio optimization under such circumstances is theoretically and computationally challenging. This work presents a novel mechanism to reach an optimal solution by encoding a variety of optimal solutions in a solution bank to guide the search process for the global investment objective formulation. It conceptualizes the role of individual solver agents that contribute optimal solutions to a bank of solutions, a super-agent solver that learns from the solution bank, and, thus reflects a knowledge-based computationally guided agents approach to investigate, analyse and reach to optimal solution for informed investment decisions. Conceptual understanding of classes of solver agents that represent varying problem formulations and, mathematically oriented deterministic solvers along with stochastic-search driven evolutionary and swarm-intelligence based techniques for optimal weights are discussed. Algorithmic implementation is presented by an enhanced neighbourhood generation mechanism in Simulated Annealing algorithm. A framework for inclusion of heuristic knowledge and human expertise from financial literature related to investment decision making process is reflected via introduction of controlled perturbation strategies using a decision matrix for neighbourhood generation.

Special-purpose constraint propagation algorithms frequently make implicit use of short supports -- by examining a subset of the variables, they can infer support (a justification that a variable-value pair may still form part of an assignment that satisfies the constraint) for all other variables and values and save substantial work -- but short supports have not been studied in their own right. The two main contributions of this paper are the identification of short supports as important for constraint propagation, and the introduction of HaggisGAC, an efficient and effective general purpose propagation algorithm for exploiting short supports. Given the complexity of HaggisGAC, we present it as an optimised version of a simpler algorithm ShortGAC. Although experiments demonstrate the efficiency of ShortGAC compared with other general-purpose propagation algorithms where a compact set of short supports is available, we show theoretically and experimentally that HaggisGAC is even better. We also find that HaggisGAC performs better than GAC-Schema on full-length supports. We also introduce a variant algorithm HaggisGAC-Stable, which is adapted to avoid work on backtracking and in some cases can be faster and have significant reductions in memory use. All the proposed algorithms are excellent for propagating disjunctions of constraints. In all experiments with disjunctions we found our algorithms to be faster than Constructive Or and GAC-Schema by at least an order of magnitude, and up to three orders of magnitude.

Supervised (linear) embedding models like Wsabie and PSI have proven successful at ranking, recommendation and annotation tasks. However, despite being scalable to large datasets they do not take full advantage of the extra data due to their linear nature, and typically underfit. We propose a new class of models which aim to provide improved performance while retaining many of the benefits of the existing class of embedding models. Our new approach works by iteratively learning a linear embedding model where the next iteration's features and labels are reweighted as a function of the previous iteration. We describe several variants of the family, and give some initial results.

We discuss theoretical aspects of the product rule for classification problems in supervised machine learning for the case of combining classifiers. We show that (1) the product rule arises from the MAP classifier supposing equivalent priors and conditional independence given a class; (2) under some conditions, the product rule is equivalent to minimizing the sum of the squared distances to the respective centers of the classes related with different features, such distances being weighted by the spread of the classes; (3) observing some hypothesis, the product rule is equivalent to concatenating the vectors of features. With the advance of the Machine Learning field, and the discovery of many different techniques, the subject of combining multiple learners [2] eventually drove attention, in particular the problem of combining classifiers. Many different methods appeared, and soon they were compared in terms of efficiency in solving problems. The product rule has been present in some of these works (e.g., [1, 7, 3, 6, 5, 4, 8]), in contexts ranging from the accuracy of the different combination rules to some analytical properties of the different methods.

Many applications in data analysis rely on the decomposition of a data matrix into a low-rank and a sparse component. Existing methods that tackle this task use the nuclear norm and L1-cost functions as convex relaxations of the rank constraint and the sparsity measure, respectively, or employ thresholding techniques. We propose a method that allows for reconstructing and tracking a subspace of upper-bounded dimension from incomplete and corrupted observations. It does not require any a priori information about the number of outliers. The core of our algorithm is an intrinsic Conjugate Gradient method on the set of orthogonal projection matrices, the so-called Grassmannian. Non-convex sparsity measures are used for outlier detection, which leads to improved performance in terms of robustly recovering and tracking the low-rank matrix. In particular, our approach can cope with more outliers and with an underlying matrix of higher rank than other state-of-the-art methods.

The problem of topic modeling can be seen as a generalization of the clustering problem, in that it posits that observations are generated due to multiple latent factors (e.g., the words in each document are generated as a mixture of several active topics, as opposed to just one). This increased representational power comes at the cost of a more challenging unsupervised learning problem of estimating the topic probability vectors (the distributions over words for each topic), when only the words are observed and the corresponding topics are hidden. We provide a simple and efficient learning procedure that is guaranteed to recover the parameters for a wide class of mixture models, including the popular latent Dirichlet allocation (LDA) model. For LDA, the procedure correctly recovers both the topic probability vectors and the prior over the topics, using only trigram statistics (i.e., third order moments, which may be estimated with documents containing just three words). The method, termed Excess Correlation Analysis (ECA), is based on a spectral decomposition of low order moments (third and fourth order) via two singular value decompositions (SVDs). Moreover, the algorithm is scalable since the SVD operations are carried out on $k\times k$ matrices, where $k$ is the number of latent factors (e.g. the number of topics), rather than in the $d$-dimensional observed space (typically $d \gg k$).