We introduce a Gaussian process-based model for handling of non-stationarity. The warping is achieved non-parametrically, through imposing a prior on the relative change of distance between subsequent observation inputs. The model allows the use of general gradient optimization algorithms for training and incurs only a small computational overhead on training and prediction. The model finds its applications in forecasting in non-stationary time series with either gradually varying volatility, presence of change points, or a combination thereof. We evaluate the model on synthetic and real-world time series data comparing against both baseline and known state-of-the-art approaches and show that the model exhibits state-of-the-art forecasting performance at a lower implementation and computation cost.

ABSTRACT The V oxCeleb Speaker Recognition Challenge 2019 aimed to assess how well current speaker recognition technology is able to identify speakers in unconstrained or'in the wild' data. It consisted of: (i) a publicly available speaker recognition dataset from Y ouTube videos together with ground truth annotation and standardised evaluation software; and (ii) a public challenge and workshop held at Interspeech 2019 in Graz, Austria. This paper outlines the challenge and provides its baselines, results and discussions. Index T erms-- speaker verification, unconstrained conditions 1. INTRODUCTION The V oxCeleb Speaker Recognition Challenge (V oxSRC) 2019 was the first of a new series of speaker recognition challenges that are intended to be hosted annually. V oxSRC 2019 consisted of: (i) a publicly available speaker recognition dataset with speech segments'in the wild', together with ground truth annotations and standardised evaluation software; and (ii) a public challenge and workshop held at Interspeech 2019 in Graz, Austria.

We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led to the observed outcome. This approach uses new information in hindsight, rather than employing foresight. Somewhat surprisingly, we show that value functions can be rewritten through this lens, yielding a new family of algorithms. We study the properties of these algorithms, and empirically show that they successfully address important credit assignment challenges, through a set of illustrative tasks.

Image synthesis is currently one of the most addressed image processing topic in computer vision and deep learning fields of study. Researchers have tackled this problem focusing their efforts on its several challenging problems, e.g. image quality and size, domain and pose changing, architecture of the networks, and so on. Above all, producing images belonging to different domains by using a single architecture is a very relevant goal for image generation. In fact, a single multi-domain network would allow greater flexibility and robustness in the image synthesis task than other approaches. This paper proposes a novel architecture and a training algorithm, which are able to produce multi-domain outputs using a single network. A small portion of a dataset is intentionally used, and there are no hard-coded labels (or classes). This is achieved by combining a conditional Generative Adversarial Network (cGAN) for image generation and a Meta-Learning algorithm for domain switch, and we called our approach MetalGAN. The approach has proved to be appropriate for solving the multi-domain problem and it is validated on facial attribute transfer, using CelebA dataset.

Recently there has been an increase in the studies on time - series data mining specifically time - series clustering due to the vast existe nce of time - series in various domains. The large volume of data in the form of time - series make s it necessary to employ various techniques such as clustering to understand the data and to extract information and hidden patterns. In the field of clustering specifically, time - series clustering, the most important aspects are the similarity measure used and the algorithm employed to conduct the clustering. In this paper, a new similarity measure for time - series clustering is developed based on a combination of a simple representation of time - series, slope of each segment of time - series, Euclidean distance and the so - called dynamic time warping. It is proved in this paper that the proposed distance measure is metric and thus indexing can be applied. For the task of clustering, the Particle Swarm Optimization algorithm is employed. The proposed similarity measure is compared to three existing measures in terms of various criteria used for the evaluation of clustering algorithms. The results indicate that the propo sed similarity measure outperforms the rest in almost every dataset used in this paper.

Quality Diversity (QD) algorithms like Novelty Search with Local Competition (NSLC) and MAP-Elites are a new class of population-based stochastic algorithms designed to generate a diverse collection of quality solutions. Meanwhile, variants of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) are among the best-performing derivative-free optimizers in single-objective continuous domains. This paper proposes a new QD algorithm called Covariance Matrix Adaptation MAP-Elites (CMA-ME). Our new algorithm combines the dynamic self-adaptation techniques of CMA-ES with archiving and mapping techniques for maintaining diversity in QD. Results from experiments with standard continuous optimization benchmarks show that CMA-ME finds better-quality solutions than MAP-Elites; similarly, results on the strategic game Hearthstone show that CMA-ME finds both a higher overall quality and broader diversity of strategies than both CMA-ES and MAP-Elites. Overall, CMA-ME more than doubles the performance of MAP-Elites using standard QD performance metrics. These results suggest that QD algorithms augmented by operators from state-of-the-art optimization algorithms can yield high-performing methods for simultaneously exploring and optimizing continuous search spaces, with significant applications to design, testing, and reinforcement learning among other domains. Code is available for both the continuous optimization benchmark (https://github.com/tehqin/QualDivBenchmark) and Hearthstone (https://github.com/tehqin/EvoStone) domains.

Clustering with variable selection is a challenging but critical task for modern small-n-large-p data. Existing methods based on Gaussian mixture models or sparse K-means provide solutions to continuous data. With the prevalence of RNA-seq technology and lack of count data modeling for clustering, the current practice is to normalize count expression data into continuous measures and apply existing models with Gaussian assumption. In this paper, we develop a negative binomial mixture model with gene regularization to cluster samples (small $n$) with high-dimensional gene features (large $p$). EM algorithm and Bayesian information criterion are used for inference and determining tuning parameters. The method is compared with sparse Gaussian mixture model and sparse K-means using extensive simulations and two real transcriptomic applications in breast cancer and rat brain studies. The result shows superior performance of the proposed count data model in clustering accuracy, feature selection and biological interpretation by pathway enrichment analysis.

Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to pruning literature, deep neural networks are known to be susceptible to adversarial examples, which may pose risks in security- or safety-critical applications. Intuition suggests that there is an inherent trade-off between sparsity and robustness such that these characteristics could not co-exist. We perform an extensive empirical evaluation and analysis testing the Lottery Ticket Hypothesis with adversarial training and show this approach enables us to find sparse, robust neural networks. Code for reproducing experiments is available here: https://github.com/justincosentino/robust-sparse-networks.

Given a data set, PCA aims at finding a sequence of orthogonal vectors that repr esent the directions of largest variance. By capturing these directions, the princ ipal components offer a way to compress the data with minimum information loss. However, principal components are usually linear combinations of all original features. That is, the weights in the linear combinations (known as loadings) are typically nonzero. I n this sense, it is difficult to give a good physical interpretation. During the past decade, various sparse principal component analysis (SPCA) approaches have been developed to improve the interpretabili ty of principal components. SPCA is an extension of PCA that aims at finding sparse loading vectors capturing the maximum amount of variance in the data. These SPCA methods ca n be categorized into two groups: block methods [16,20,22-24,32] and deflati on methods [5,7,25,28]. Block methods aims to find all sparse loadings together, whil e deflation methods compute one loading at a time.

We consider the problem of learning in episodic finite-horizon Markov decision processes with unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves $\mathcal{\tilde{O}}(L|X|^2\sqrt{|A|T})$ regret with high probability, where $L$ is the horizon, $|X|$ is the number of states, $|A|$ is the number of actions, and $T$ is the number of episodes. To the best of our knowledge, our algorithm is the first one to ensure {$\mathcal{\tilde{O}}(\sqrt{T})$} regret in this challenging setting. Our key technical contribution is to introduce an optimistic loss estimator that is inversely weighted by an $\textit{upper occupancy bound}$.