Dr. Constantinos Daskalakis, the Greek MIT professor who solved the puzzle of the Nash Equilibria, said that one of the main concerns of humanity is the credibility of technology. Speaking in a packed auditorium at the Aristotle University of Thessaloniki last week, the Greek genius mesmerised the audience with his theories on Artificial Intelligence and its importance on the future of mankind. According to Dr. Daskalakis, today one of the main concerns of humanity is the credibility of technology. Speaking on Artificial Intelligence, he said that, "There are big issues of reliability and one of the reasons is that when the data you feed the algorithm are incomplete or unrepresentative, can lead to faulty or insufficient mental functions. For example, why did a (driver-less) Tesla car smash into a truck stopped in the left lane? Maybe because the data that was entered to train the algorithm did not include the possibility that a car has stalled in the left lane of the highway because this is rarely happening. The algorithm will process the incomplete data we have given it and incorporate this shortage."

We analyse a linear regression problem with nonconvex regularization called smoothly clipped absolute deviation (SCAD) under an overcomplete Gaussian basis for Gaussian random data. We propose an approximate message passing (AMP) algorithm considering nonconvex regularization, namely SCAD-AMP, and analytically show that the stability condition corresponds to the de Almeida--Thouless condition in spin glass literature. Through asymptotic analysis, we show the correspondence between the density evolution of SCAD-AMP and the replica symmetric solution. Numerical experiments confirm that for a sufficiently large system size, SCAD-AMP achieves the optimal performance predicted by the replica method. Through replica analysis, a phase transition between replica symmetric (RS) and replica symmetry breaking (RSB) region is found in the parameter space of SCAD. The appearance of the RS region for a nonconvex penalty is a significant advantage that indicates the region of smooth landscape of the optimization problem. Furthermore, we analytically show that the statistical representation performance of the SCAD penalty is better than that of L1-based methods, and the minimum representation error under RS assumption is obtained at the edge of the RS/RSB phase. The correspondence between the convergence of the existing coordinate descent algorithm and RS/RSB transition is also indicated.

We study the detailed path-wise behavior of the discrete-time Langevin algorithm for non-convex Empirical Risk Minimization (ERM) through the lens of metastability, adopting some techniques from Berglund and Gentz. For a particular local optimum of the empirical risk, with an arbitrary initialization, we show that, with high probability, one of the two mutually exclusive events will occur: either the Langevin trajectory ends up somewhere outside the $\varepsilon$-neighborhood of this particular optimum within a short recurrence time; or it enters this $\varepsilon$-neighborhood by the recurrence time and stays there until an exponentially long escape time. We call this phenomenon empirical metastability. This two-timescale characterization aligns nicely with the existing literature in the following two senses. First, the recurrence time is dimension-independent, and resembles the convergence time of deterministic Gradient Descent (GD). However unlike GD, the Langevin algorithm does not require strong conditions on local initialization, and has the possibility of eventually visiting all optima. Second, the scaling of the escape time is consistent with the Eyring-Kramers law, which states that the Langevin scheme will eventually visit all local minima, but it will take an exponentially long time to transit among them. We apply this path-wise concentration result in the context of statistical learning to examine local notions of generalization and optimality.

A substantial progress in development of new and efficient tensor factorization techniques has led to an extensive research of their applicability in recommender systems field. Tensor-based recommender models push the boundaries of traditional collaborative filtering techniques by taking into account a multifaceted nature of real environments, which allows to produce more accurate, situational (e.g. context-aware, criteria-driven) recommendations. Despite the promising results, tensor-based methods are poorly covered in existing recommender systems surveys. This survey aims to complement previous works and provide a comprehensive overview on the subject. To the best of our knowledge, this is the first attempt to consolidate studies from various application domains in an easily readable, digestible format, which helps to get a notion of the current state of the field. We also provide a high level discussion of the future perspectives and directions for further improvement of tensor-based recommendation systems.

We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber epsilon-contamination model and in heavy-tailed settings. Our workhorse is a novel robust variant of gradient descent, and we provide conditions under which our gradient descent variant provides accurate estimators in a general convex risk minimization problem. We provide specific consequences of our theory for linear regression, logistic regression and for estimation of the canonical parameters in an exponential family. These results provide some of the first computationally tractable and provably robust estimators for these canonical statistical models. Finally, we study the empirical performance of our proposed methods on synthetic and real datasets, and find that our methods convincingly outperform a variety of baselines.

The ConditionaL Neural Networks (CLNN) and the Masked ConditionaL Neural Networks (MCLNN) exploit the nature of multi-dimensional temporal signals. The CLNN captures the conditional temporal influence between the frames in a window and the mask in the MCLNN enforces a systematic sparseness that follows a filterbank-like pattern over the network links. The mask induces the network to learn about time-frequency representations in bands, allowing the network to sustain frequency shifts. Additionally, the mask in the MCLNN automates the exploration of a range of feature combinations, usually done through an exhaustive manual search. We have evaluated the MCLNN performance using the Ballroom and Homburg datasets of music genres. MCLNN has achieved accuracies that are competitive to state-of-the-art handcrafted attempts in addition to models based on Convolutional Neural Networks.

Training complex machine learning models for prediction often requires a large amount of data that is not always readily available. Leveraging these external datasets from related but different sources is therefore an important task if good predictive models are to be built for deployment in settings where data can be rare. In this paper we propose a novel approach to the problem in which we use multiple GAN architectures to learn to translate from one dataset to another, thereby allowing us to effectively enlarge the target dataset, and therefore learn better predictive models than if we simply used the target dataset. We show the utility of such an approach, demonstrating that our method improves the prediction performance on the target domain over using just the target dataset and also show that our framework outperforms several other benchmarks on a collection of real-world medical datasets.

We propose a one-class neural network (OC-NN) model to detect anomalies in complex data sets. OC-NN combines the ability of deep networks to extract progressively rich representation of data with the one-class objective of creating a tight envelope around normal data. The OC-NN approach breaks new ground for the following crucial reason: data representation in the hidden layer is driven by the OC-NN objective and is thus customized for anomaly detection. This is a departure from other approaches which use a hybrid approach of learning deep features using an autoencoder and then feeding the features into a separate anomaly detection method like one-class SVM (OC-SVM). The hybrid OC-SVM approach is suboptimal because it is unable to influence representational learning in the hidden layers. A comprehensive set of experiments demonstrate that on complex data sets (like CIFAR and PFAM), OC-NN significantly outperforms existing state-of-the-art anomaly detection methods.

Assessing the impact of the individual actions performed by soccer players during games is a crucial aspect of the player recruitment process. Unfortunately, most traditional metrics fall short in addressing this task as they either focus on rare events like shots and goals alone or fail to account for the context in which the actions occurred. This paper introduces a novel advanced soccer metric for valuing any type of individual player action on the pitch, be it with or without the ball. Our metric values each player action based on its impact on the game outcome while accounting for the circumstances under which the action happened. When applied to on-the-ball actions like passes, dribbles, and shots alone, our metric identifies Argentine forward Lionel Messi, French teenage star Kylian Mbapp\'e, and Belgian winger Eden Hazard as the most effective players during the 2016/2017 season.

We propose an efficient stochastic variational approach to GP classification building on Polya- Gamma data augmentation and inducing points, which is based on closed-form updates of natural gradients. We evaluate the algorithm on real-world datasets containing up to 11 million data points and demonstrate that it is up to three orders of magnitude faster than the state-of-the-art while being competitive in terms of prediction performance.