We propose a method for generating an electrocardiogram (ECG) signal for one cardiac cycle using a variational autoencoder. Using this method we extracted a vector of new 25 features, which in many cases can be interpreted. The generated ECG has quite natural appearance. The low value of the Maximum Mean Discrepancy metric, 0.00383, indicates good quality of ECG generation too. The extracted new features will help to improve the quality of automatic diagnostics of cardiovascular diseases. Also, generating new synthetic ECGs will allow us to solve the issue of the lack of labeled ECG for use them in supervised learning.

We study multi-armed bandit problems with supply or budget c onstraints. Multi-armed bandits is a simple model for exploration-exploitation tradeoff, i.e., the tension between acquiring new information and making optimal decisions. It is an active re search area, spanning computer science, operations research, and economics. Supply/budget constr aints arise in many realistic applications, e.g., a seller who dynamically adjusts the prices may have a limite d inventory, and an algorithm that optimizes ad placement is constrained by the advertise rs' budgets. Other motivating examples concern repeated actions, crowdsourcing markets, and netw ork routing and scheduling. We consider a general model called Bandits with Knapsacks (BwK), which subsumes the examples mentioned above.

The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff. However, standard formulations do not take into account risk. In online decision making systems, risk is a primary concern. In this regard, the mean-variance risk measure is one of the most common objective functions. Existing algorithms for mean-variance optimization in the context of MAB problems have unrealistic assumptions on the reward distributions. We develop Thompson Sampling-style algorithms for mean-variance MAB and provide comprehensive regret analyses for Gaussian and Bernoulli bandits with fewer assumptions. Our algorithms achieve the best known regret bounds for mean-variance MABs and also attain the information-theoretic bounds in some parameter regimes. Empirical simulations show that our algorithms significantly outperform existing LCB-based algorithms for all risk tolerances.

Martel, Jozef Adamcik, Matthew Cook, Richard H. R. Hahnloser Abstract --Serial section electron microscopy (ssEM) is a widely used technique for obtaining volumetric information of biological tissues at nanometer scale. However, accurate 3D reconstructions of identified cellular structures and volumetric quantifications require precise estimates of section thickness and anisotropy (or stretching) along the XY imaging plane. In fact, many image processing algorithms simply assume isotropy within the imaging plane. T o ameliorate this problem, we present a method for estimating thickness and stretching of electron microscopy sections using nonparametric Bayesian regression of image statistics. We verify our thickness and stretching estimates using direct measurements obtained by atomic force microscopy (AFM) and show that our method has a lower estimation error compared to a recent indirect thickness estimation method as well as a relative Z coordinate estimation method. Furthermore, we have made the first dataset of ssSEM images with directly measured section thickness values publicly available for the evaluation of indirect thickness estimation methods. I NTRODUCTION Electron microscopy (EM) has enabled imaging of nano-scale neuroanatomical structures such as synapses. Serial section Scanning Electron Microscopy (ssSEM) and serial section Transmission Electron Microscopy (ssTEM) are used to inspect tissue volumes on the scale of tens to hundreds of micrometers in each dimension. Tissue sections suitable for ssEM typically have a thickness that ranges from 30 nm to 70 nm .

Federated learning systems are vulnerable to attacks from malicious clients. As the central server in the system cannot govern the behaviors of the clients, a rogue client may initiate an attack by sending malicious model updates to the server, so as to degrade the learning performance or enforce targeted model poisoning attacks (a.k.a. Therefore, timely detecting these malicious model updates and the underlying attackers becomes critically important. In this work, we propose a new framework for robust federated learning where the central server learns to detect and remove the malicious model updates using a powerful detection model, leading to targeted defense . We evaluate our solution in both image classification and sentiment analysis tasks with a variety of machine learning models. Experimental results show that our solution ensures robust federated learning that is resilient to both the Byzantine attacks and the targeted model poisoning attacks. 1 Introduction Federated learning (FL) comes as a new distributed machine learning (ML) paradigm where multiple clients (e.g., mobile devices) collaboratively train an ML model without revealing their private data [ McMahan et al., 2017; Y ang et al., 2019b; Kairouz et al., 2019 ] . In a typical FL setting, a central server is used to maintain a global model and coordinate the clients. Each client transfers the local model updates to the central server for immediate aggregation, while keeping the raw data in their local storage.

Granger causality is a fundamental technique for causal inference in time series data, commonly used in the social and biological sciences. Typical operationalizations of Granger causality make a strong assumption that every time point of the effect time series is influenced by a combination of other time series with a fixed time delay. The assumption of fixed time delay also exists in Transfer Entropy, which is considered to be a non-linear version of Granger causality. However, the assumption of the fixed time delay does not hold in many applications, such as collective behavior, financial markets, and many natural phenomena. To address this issue, we develop variable-lag Granger causality and Transfer Entropy, generalizations of both Granger causality and Transfer Entropy that relax the assumption of the fixed time delay and allows causes to influence effects with arbitrary time delays. In addition, we propose a method for inferring both variable-lag Granger causality and Transfer Entropy relations. We demonstrate our approach on an application for studying coordinated collective behavior and other real-world casual-inference datasets and show that our proposed approaches perform better than several existing methods in both simulated and real-world datasets. Our approach can be applied in any domain of time series analysis. The software of this work is available in the R package: VLTimeSeriesCausality.

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early stopped unconstrained mirror descent algorithms applied to the unregularized empirical risk with squared loss for linear models and kernel methods. We identify a link between offset Rademacher complexities and potential-based analysis of mirror descent that allows disentangling statistics from optimization in the analysis of such algorithms. Our main result characterizes the statistical performance of the path traced by the iterates of mirror descent in terms of offset complexities of certain function classes depending only on the choice of the mirror map, initialization point, step-size, and number of iterations. We apply our theory to recover, in a rather clean and elegant manner, some of the recent results in the implicit regularization literature, while also showing how to improve upon them in some settings.

For instance, penalties are used to improve generalization, prune neurons or reduce the rank of tensors of weights. Therefore, usual penalties are mostly empirical and user-defined, and integrated to the loss as follows: L( w) null( w) r (w), with w the vector of all parameters in the network, null( w) the error term and r (w) the penalty term. From a Bayesian point of view, optimizing such a loss L is equivalent to finding the Maximum A Posteriori (MAP) of the parameters w given the training data and a prior α exp( r). Indeed, assuming that the loss null is a log-likelihood loss, namely, null(w) ln p w( D) with dataset D, then minimizing L is equivalent to minimizing L MAP(w) ln p w(D) ln(α (w)). Thus, within the MAP framework, we can interpret the penalty term r as the influence of a prior α [14]. However, the MAP approximates the Bayesian posterior very roughly, by taking its maximum. Variational Inference (VI) provides a variational posterior distribution rather than a single value, hopefully representing the Bayesian posterior much better. VI looks for the best posterior approximation within a family β u(w) of approximate posteriors over w, parameterized Inria, Team TAU, Gif-sur-Yvette, France † Facebook, France 1 arXiv:2002.00178v1

The global sports tech ecosystem is awash with early-stage companies and entrepreneurs who have brought to market all manner of novel solutions and innovations. In recent years, the number of startups specialising in areas such as athletic performance and analytics, artificial intelligence (AI), big data, fantasy sports, gaming, content production and in-venue technology has proliferated, contributing to rapid growth across the sports tech sector. Already estimated to be worth US$8.9 billion, the global sports tech market is expected to triple in value in the next five years. But, as any investor worth their salt will know, not all new technologies make for attractive investment propositions. Here, with the help of Sports Loft founder Charlie Greenwood, SportsPro profiles the innovators whose products and services should be on every sports tech investor's radar.

In the space of a single year, South African agritech enterprise Aerobotics has won numerous awards and made strategic inroads into the massively competitive US agriculture industry. Propelled by world-leading technology, the South African success story is poised to mushroom into a truly global data and analytics software company serving the entire agriculture value chain. Aerobotics, which as little as a year ago was nominated as one of South Africa's most exciting startups, turns imagery into actionable data so that any issues on the farm, or elsewhere in the value chain, can be identified and resolved before they become problems. In essence, Aerobotics exposes what the naked eye cannot see in order to solve problems and make accurate projections, translating into improved yields and profitability. The company's CEO, James Paterson, says the business is ready to build on its highly successful launch in the US and strategically drop further roots and extend services in numerous regions around the world.