We derive expressions for the predicitive information rate (PIR) for the class of autoregressive Gaussian processes AR(N), both in terms of the prediction coefficients and in terms of the power spectral density. The latter result suggests a duality between the PIR and the multi-information rate for processes with mutually inverse power spectra (i.e. with poles and zeros of the transfer function exchanged). We investigate the behaviour of the PIR in relation to the multi-information rate for some simple examples, which suggest, somewhat counter-intuitively, that the PIR is maximised for very `smooth' AR processes whose power spectra have multiple poles at zero frequency. We also obtain results for moving average Gaussian processes which are consistent with the duality conjectured earlier. One consequence of this is that the PIR is unbounded for MA(N) processes.

We develop a highly scalable optimization method called "hierarchical group-thresholding" for solving a multi-task regression model with complex structured sparsity constraints on both input and output spaces. Despite the recent emergence of several efficient optimization algorithms for tackling complex sparsity-inducing regularizers, true scalability in practical high-dimensional problems where a huge amount (e.g., millions) of sparsity patterns need to be enforced remains an open challenge, because all existing algorithms must deal with ALL such patterns exhaustively in every iteration, which is computationally prohibitive. Our proposed algorithm addresses the scalability problem by screening out multiple groups of coefficients simultaneously and systematically. We employ a hierarchical tree representation of group constraints to accelerate the process of removing irrelevant constraints by taking advantage of the inclusion relationships between group sparsities, thereby avoiding dealing with all constraints in every optimization step, and necessitating optimization operation only on a small number of outstanding coefficients. In our experiments, we demonstrate the efficiency of our method on simulation datasets, and in an application of detecting genetic variants associated with gene expression traits.

In a context where most published articles are devoted to the development of "new methods", comparison studies are generally appreciated by readers but surprisingly given poor consideration by many scientific journals. In connection with recent articles on over-optimism and epistemology published in Bioinformatics, this letter stresses the importance of neutral comparison studies for the objective evaluation of existing methods and the establishment of standards by drawing parallels with clinical research.

It is now common to see practical applications, for example in bioinformatics and computer vision, where the dimensionality of the data is in the order of hundreds, thousands and even tens of thousands. It is known that learning in such a high dimensional regime is feasible only if the quantity to be estimated satisfies some regularity assumptions [24]. In particular, the idea behind, so called, sparsity is that the quantity of interest depends only on a few relevant variables (dimensions). In turn, this latter assumption is often at the basis of the construction of interpretable data models, since the relevant dimensions allow for a compact, hence interpretable, representation. An instance of the above situation is the problem of learning from samples a multivariate function which depends only on a (possibly small) subset of relevant variables. Detecting such variables is the problem of variable selection. Largely motivated by recent advances in compressed sensing [15, 25], the above problem has been extensively studied under the assumption that the function of interest (target function) depends linearly to the relevant variables.

We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model free, non-parametric approach for calculation of an approximate solution to the control problem. This formulation admits a decomposition of the problem into an invariant and task dependent component. Consequently, we make much more efficient use of the sample data compared to previous sample based approaches in this domain, e.g., by allowing sample re-use across tasks. Numerical examples on test problems, which illustrate the sample efficiency, are provided.

A vast amount of textual web streams is influenced by events or phenomena emerging in the real world. The social web forms an excellent modern paradigm, where unstructured user generated content is published on a regular basis and in most occasions is freely distributed. The present Ph.D. Thesis deals with the problem of inferring information - or patterns in general - about events emerging in real life based on the contents of this textual stream. We show that it is possible to extract valuable information about social phenomena, such as an epidemic or even rainfall rates, by automatic analysis of the content published in Social Media, and in particular Twitter, using Statistical Machine Learning methods. An important intermediate task regards the formation and identification of features which characterise a target event; we select and use those textual features in several linear, non-linear and hybrid inference approaches achieving a significantly good performance in terms of the applied loss function. By examining further this rich data set, we also propose methods for extracting various types of mood signals revealing how affective norms - at least within the social web's population - evolve during the day and how significant events emerging in the real world are influencing them. Lastly, we present some preliminary findings showing several spatiotemporal characteristics of this textual information as well as the potential of using it to tackle tasks such as the prediction of voting intentions.

In the supervised learning setting termed Multiple-Instance Learning (MIL), the examples are bags of instances, and the bag label is a function of the labels of its instances. Typically, this function is the Boolean OR. The learner observes a sample of bags and the bag labels, but not the instance labels that determine the bag labels. The learner is then required to emit a classification rule for bags based on the sample. MIL has numerous applications, and many heuristic algorithms have been used successfully on this problem, each adapted to specific settings or applications. In this work we provide a unified theoretical analysis for MIL, which holds for any underlying hypothesis class, regardless of a specific application or problem domain. We show that the sample complexity of MIL is only poly-logarithmically dependent on the size of the bag, for any underlying hypothesis class. In addition, we introduce a new PAC-learning algorithm for MIL, which uses a regular supervised learning algorithm as an oracle. We prove that efficient PAC-learning for MIL can be generated from any efficient non-MIL supervised learning algorithm that handles one-sided error. The computational complexity of the resulting algorithm is only polynomially dependent on the bag size.

The early classifications of the computational complexity of planning under various restrictions in STRIPS (Bylander) and SAS+ (Baeckstroem and Nebel) have influenced following research in planning in many ways. We go back and reanalyse their subclasses, but this time using the more modern tool of parameterized complexity analysis. This provides new results that together with the old results give a more detailed picture of the complexity landscape. We demonstrate separation results not possible with standard complexity theory, which contributes to explaining why certain cases of planning have seemed simpler in practice than theory has predicted. In particular, we show that certain restrictions of practical interest are tractable in the parameterized sense of the term, and that a simple heuristic is sufficient to make a well-known partial-order planner exploit this fact.

In this paper, we propose a framework to study a general class of strategic behavior in voting, which we call vote operations. We prove the following theorem: if we fix the number of alternatives, generate $n$ votes i.i.d. according to a distribution $\pi$, and let $n$ go to infinity, then for any $\epsilon >0$, with probability at least $1-\epsilon$, the minimum number of operations that are needed for the strategic individual to achieve her goal falls into one of the following four categories: (1) 0, (2) $\Theta(\sqrt n)$, (3) $\Theta(n)$, and (4) $\infty$. This theorem holds for any set of vote operations, any individual vote distribution $\pi$, and any integer generalized scoring rule, which includes (but is not limited to) almost all commonly studied voting rules, e.g., approval voting, all positional scoring rules (including Borda, plurality, and veto), plurality with runoff, Bucklin, Copeland, maximin, STV, and ranked pairs. We also show that many well-studied types of strategic behavior fall under our framework, including (but not limited to) constructive/destructive manipulation, bribery, and control by adding/deleting votes, margin of victory, and minimum manipulation coalition size. Therefore, our main theorem naturally applies to these problems.

We examine a fundamental problem that models various active sampling setups, such as network tomography. We analyze sampling of a multivariate normal distribution with an unknown expectation that needs to be estimated: in our setup it is possible to sample the distribution from a given set of linear functionals, and the difficulty addressed is how to optimally select the combinations to achieve low estimation error. Although this problem is in the heart of the field of optimal design, no efficient solutions for the case with many functionals exist. We present some bounds and an efficient sub-optimal solution for this problem for more structured sets such as binary functionals that are induced by graph walks.