Machine learning applications often require efficient statistical procedures to process potentially massive amount of high dimensional data. Motivated by such applications, the broad objective of our study is deriving learning procedures with optimal statistical properties, and, at the same time, computational complexities proportional to the generalization properties allowed by the data, rather than their raw amount [5]. In this paper, we focus on iterative regularization as a viable approach towards this goal. The key observation behind these techniques is that iterative optimization schemes applied to scattered, noisy data exhibit a self-regularizing property, in the sense that early termination (early-stop) of the iterative process has a regularizing effect [19, 22]. Indeed, iterative regularization algorithms are classical in inverse problems [14], and have been recently considered in machine learning [6, 32, 2, 4, 8, 24], where they have been proved to achieve optimal learning bounds, matching those of variational regularization schemes such as Tikhonov [7, 29]. 1 In this paper, we consider an iterative regularization algorithm for the square loss, based on a recursive procedure updating the solution after processing one training set point at each iteration. Methods of the latter form, often broadly referred to as online learning algorithms, have become standard in the processing of large data-sets, because of their often low iteration cost and good practical performance. Theoretical studies for this class of algorithms have been developed within different frameworks.

This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem. Unlike most previous work, we give results that are general enough to include cases in which no minimum exists, as occurs typically, for instance, with standard boosting algorithms. Concretely, we first show that any sequence of predictors minimizing convex risk over the source distribution will converge to this unique model when the class of predictors is linear (but potentially of infinite dimension). Secondly, we show the same result holds for \emph{empirical} risk minimization whenever this class of predictors is finite dimensional, where the essential technical contribution is a norm-free generalization bound.

Determining the finite-sample behavior of risk in the problem of regression is arguably one of the most basic problems of Learning Theory and Statistics. This behavior can be studied in substantial generality with the tools of empirical process theory. When functions in a given convex class are uniformly bounded, one may verify the socalled "Bernstein condition." The condition--which relates the variance of the increments of the empirical process to their expectation--implies a certain localization phenomenon around the optimum and forms the basis of the analysis via local Rademacher complexities. The technique has been developed in [9, 8, 5, 2, 4], among others, based on Talagrand's celebrated concentration inequality for the supremum of an empirical process. In a recent pathbreaking paper, [14] showed that a large part of this heavy machinery is not necessary for obtaining tight upper bounds on excess loss, even--and especially--if functions are unbounded. Mendelson observed that only one-sided control of the tail is required in the deviation inequality, and, thankfully, it is the tail that can be controlled under very mild assumptions. In a parallel line of work, the search within the online learning setting for an analogue of "localization" has led to a notion of an "offset" Rademacher process [17], yielding--in a rather clean manner--optimal rates for minimax regret in online supervised learning. It was also shown that the supremum of the offset process is a lower bound on the minimax value, thus establishing its intrinsic nature.

The PAC-Bayesian approach is a powerful set of techniques to derive non- asymptotic risk bounds for random estimators. The corresponding optimal distribution of estimators, usually called the Gibbs posterior, is unfortunately intractable. One may sample from it using Markov chain Monte Carlo, but this is often too slow for big datasets. We consider instead variational approximations of the Gibbs posterior, which are fast to compute. We undertake a general study of the properties of such approximations. Our main finding is that such a variational approximation has often the same rate of convergence as the original PAC-Bayesian procedure it approximates. We specialise our results to several learning tasks (classification, ranking, matrix completion),discuss how to implement a variational approximation in each case, and illustrate the good properties of said approximation on real datasets.

It is well-known that learning predictive models capable of dealing with outputs that are richer than binary outputs (e.g., multiclass or multilabel) and for which theoretical guarantees exist is still a realm of intensive investigations. From a practical standpoint, a lot of relaxations for learning with complex outputs have been devised. A common approach consists in decomposing the output space into "simpler" spaces so that the learning problem at hand can be reduced to a few easier (i.e., binary) learning tasks. For instance, this is the idea spurred by the Error-Correcting Output Codes (Dietterich & Bakiri, 1995) that makes possible to reduce multiclass or multilabel problems into binary classification tasks,e.g., (Allwein et al., 2001; Mroueh et al., 2012; Read et al., 2011; Tsoumakas & Vlahavas, 2007; Zhang & Schneider, 2012). In our work, we study the problem of complex output prediction by focusing on prediction functions that take the form of a weighted majority vote over a set of complex output classifiers (or voters). Recall that ensemble methods can all be seen as majority vote learning procedures (Dietterich, 2000; Re & Valentini, 2012). Methods such as Bagging (Breiman, 1996), Boosting (Schapire & Singer, 1999) and Random Forests (Breiman, 2001) are representative voting methods. Cortes et al. (2014) have proposed various ensemble methods for the structured output prediction framework. Note also that majority votes are also central to the Bayesian approach (Gelman et al., 2004) with the notion of Bayesian model averaging (Domingos, 2000; Haussler et al., 1994) and most of kernel-based predictors, such as the Support Vector Machines (Boser et al., 1992; Cortes & Vapnik, 1995) may be viewed as weighted majority votes as well: for binary classification, where the predicted class for some input x is computed as the sign of

Interpersonal relations are fickle, with close friendships often dissolving into enmity. In this work, we explore linguistic cues that presage such transitions by studying dyadic interactions in an online strategy game where players form alliances and break those alliances through betrayal. We characterize friendships that are unlikely to last and examine temporal patterns that foretell betrayal. We reveal that subtle signs of imminent betrayal are encoded in the conversational patterns of the dyad, even if the victim is not aware of the relationship's fate. In particular, we find that lasting friendships exhibit a form of balance that manifests itself through language. In contrast, sudden changes in the balance of certain conversational attributes---such as positive sentiment, politeness, or focus on future planning---signal impending betrayal.

Restricted Boltzmann machines are undirected neural networks which have been shown to be effective in many applications, including serving as initializations for training deep multi-layer neural networks. One of the main reasons for their success is the existence of efficient and practical stochastic algorithms, such as contrastive divergence, for unsupervised training. We propose an alternative deterministic iterative procedure based on an improved mean field method from statistical physics known as the Thouless-Anderson-Palmer approach. We demonstrate that our algorithm provides performance equal to, and sometimes superior to, persistent contrastive divergence, while also providing a clear and easy to evaluate objective function. We believe that this strategy can be easily generalized to other models as well as to more accurate higher-order approximations, paving the way for systematic improvements in training Boltzmann machines with hidden units.

In Dung's abstract argumentation, arguments are either acceptable or unacceptable, given a chosen notion of acceptability. This gives a coarse way to compare arguments. In this paper, we propose a counting approach for a more fine-gained assessment to arguments by counting the number of their respective attackers and defenders based on argument graph and argument game. An argument is more acceptable if the proponent puts forward more number of defenders for it and the opponent puts forward less number of attackers against it. We show that our counting model has two well-behaved properties: normalization and convergence. Then, we define a counting semantics based on this model, and investigate some general properties of the semantics.

Forward stagewise regression follows a very simple strategy for constructing a sequence of sparse regression estimates: it starts with all coefficients equal to zero, and iteratively updates the coefficient (by a small amount $\epsilon$) of the variable that achieves the maximal absolute inner product with the current residual. This procedure has an interesting connection to the lasso: under some conditions, it is known that the sequence of forward stagewise estimates exactly coincides with the lasso path, as the step size $\epsilon$ goes to zero. Furthermore, essentially the same equivalence holds outside of least squares regression, with the minimization of a differentiable convex loss function subject to an $\ell_1$ norm constraint (the stagewise algorithm now updates the coefficient corresponding to the maximal absolute component of the gradient). Even when they do not match their $\ell_1$-constrained analogues, stagewise estimates provide a useful approximation, and are computationally appealing. Their success in sparse modeling motivates the question: can a simple, effective strategy like forward stagewise be applied more broadly in other regularization settings, beyond the $\ell_1$ norm and sparsity? The current paper is an attempt to do just this. We present a general framework for stagewise estimation, which yields fast algorithms for problems such as group-structured learning, matrix completion, image denoising, and more.

A common approach to statistical learning with big-data is to randomly split it among $m$ machines and learn the parameter of interest by averaging the $m$ individual estimates. In this paper, focusing on empirical risk minimization, or equivalently M-estimation, we study the statistical error incurred by this strategy. We consider two large-sample settings: First, a classical setting where the number of parameters $p$ is fixed, and the number of samples per machine $n\to\infty$. Second, a high-dimensional regime where both $p,n\to\infty$ with $p/n \to \kappa \in (0,1)$. For both regimes and under suitable assumptions, we present asymptotically exact expressions for this estimation error. In the fixed-$p$ setting, under suitable assumptions, we prove that to leading order averaging is as accurate as the centralized solution. We also derive the second order error terms, and show that these can be non-negligible, notably for non-linear models. The high-dimensional setting, in contrast, exhibits a qualitatively different behavior: data splitting incurs a first-order accuracy loss, which to leading order increases linearly with the number of machines. The dependence of our error approximations on the number of machines traces an interesting accuracy-complexity tradeoff, allowing the practitioner an informed choice on the number of machines to deploy. Finally, we confirm our theoretical analysis with several simulations.