State space models (SSMs) are a flexible approach to modeling complex time series. However, inference in SSMs is often computationally prohibitive for long time series. Stochastic gradient MCMC (SGMCMC) is a popular method for scalable Bayesian inference for large independent data. Unfortunately when applied to dependent data, such as in SSMs, SGMCMC's stochastic gradient estimates are biased as they break crucial temporal dependencies. To alleviate this, we propose stochastic gradient estimators that control this bias by performing additional computation in a `buffer' to reduce breaking dependencies. Furthermore, we derive error bounds for this bias and show a geometric decay under mild conditions. Using these estimators, we develop novel SGMCMC samplers for discrete, continuous and mixed-type SSMs. Our experiments on real and synthetic data demonstrate the effectiveness of our SGMCMC algorithms compared to batch MCMC, allowing us to scale inference to long time series with millions of time points.

Abstract--In the era of "big data", analysts usually explore various statistical models or machine learning methods for observed data in order to facilitate scientific discoveries or gain predictive power. Whatever data and fitting procedures are employed, a crucial step is to select the most appropriate model or method from a set of candidates. Model selection is a key ingredient in data analysis for reliable and reproducible statistical inference or prediction, and thus central to scientific studies in fields such as ecology, economics, engineering, finance, political science, biology, and epidemiology. There has been a long history of model selection techniques that arise from researches in statistics, information theory, and signal processing. A considerable number of methods have been proposed, following different philosophies and exhibiting varying performances. The purpose of this article is to bring a comprehensive overview of them, in terms of their motivation, large sample performance, and applicability. We provide integrated and practically relevant discussions on theoretical properties of state-ofthe-art model selection approaches. We also share our thoughts on some controversial views on the practice of model selection. Vast development in hardware storage, precision instrument manufacture, economic globalization, etc. have generated huge volumes of data that can be analyzed to extract useful information. Typical statistical inference or machine learning procedures learn from and make predictions on data by fitting parametric or nonparametric models (in a broad sense). However, there exists no model that is universally suitable for any data and goal. This research was funded in part by the Defense Advanced Research Projects Agency (DARPA) under grant number W911NF-18-1-0134. J. Ding and Y. Yang are with the School of Statistics, University of Minnesota, Minneapolis, Minnesota 55455, United States. V. Tarokh is with the Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina 27708, United States. Therefore, a crucial step in a typical data analysis is to consider a set of candidate models (referred to as the model class), and then select the most appropriate one. In other words, model selection is the task of selecting a statistical model from a model class, given a set of data. There have been many overview papers on model selection scattered in the communities of signal processing [1], statistics [2], machine learning [3], epidemiology [4], chemometrics [5], ecology and evolution [6]. Despite the abundant literature on model selection, existing overviews usually focus on derivations, descriptions, or applications of particular model selection principles.

Designing of touchless user interface is gaining popularity in various contexts. Using such interfaces, users can interact with electronic devices even when the hands are dirty or non-conductive. Also, user with partial physical disability can interact with electronic devices using such systems. Research in this direction has got major boost because of the emergence of low-cost sensors such as Leap Motion, Kinect or RealSense devices. In this paper, we propose a Leap Motion controller-based methodology to facilitate rendering of 2D and 3D shapes on display devices. The proposed method tracks finger movements while users perform natural gestures within the field of view of the sensor. In the next phase, trajectories are analyzed to extract extended Npen++ features in 3D. These features represent finger movements during the gestures and they are fed to unidirectional left-to-right Hidden Markov Model (HMM) for training. A one-to-one mapping between gestures and shapes is proposed. Finally, shapes corresponding to these gestures are rendered over the display using MuPad interface. We have created a dataset of 5400 samples recorded by 10 volunteers. Our dataset contains 18 geometric and 18 non-geometric shapes such as "circle", "rectangle", "flower", "cone", "sphere" etc. The proposed methodology achieves an accuracy of 92.87% when evaluated using 5-fold cross validation method. Our experiments revel that the extended 3D features perform better than existing 3D features in the context of shape representation and classification. The method can be used for developing useful HCI applications for smart display devices.

Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make mistake. It always involves a defending side, usually a classifier, and an attacking side that aims to cause incorrect output. The earliest studies on the adversarial examples for machine learning algorithms start from the information security area, which considers a much wider varieties of attacking methods. But recent research focus that popularized by the deep learning community places strong emphasis on how the "imperceivable" perturbations on the normal inputs may cause dramatic mistakes by the deep learning with supposed super-human accuracy. This paper serves to give a comprehensive introduction to a range of aspects of the adversarial deep learning topic, including its foundations, typical attacking and defending strategies, and some extended studies.

A Dynamic Bayesian Network (DBN) [1-3] is a widely used family of graphical model for representing and reasoning within dynamic systems whose progress is recorded over a discrete time intervals [4-10]. However, in some context a DBN model is not able to represent all structural information of the target process [11]. This is particularly the case when the process is more naturally described by concatenations of unfolding events rather than by a product space of preassigned set of random variables. In other situations, a relevant statement corresponding to a conditioned variable cannot be directly incorporated into a DBN model using directed edges because it is valid only for a certain combinations of values assumed by the conditioning variables. In the literature, this type of statements is sometimes referred to context-specific information [12, 13]. To circumvent these issues, collections of networks and embellishments in the form of trees have been added to the DBN framework and computationally implemented using the object-oriented programming paradigm [14]: for instance, see the developments on context-specific BNs [11, 13, 15], Bayesian Multinet [16], Similarity Networks [17] and Object-Oriented BNs [18, 19].

Despite the exceptional performance of deep neural networks (DNNs) on various machine learning tasks such as malware detection (Saxe & Berlin, 2015), face recognition (Parkhi et al., 2015) and autonomous driving (Bojarski et al., 2016), recent studies (Szegedy et al., 2014; Goodfellow et al., 2015) have shown that deep learning models are vulnerable to misclassifying inputs, known as adversarial examples, that are crafted with targeted but visually-imperceptible perturbations. While several defense mechanisms have been proposed and empirically demonstrated to be successful against existing particular attacks (Papernot et al., 2016; Goodfellow et al., 2015), new attacks (Carlini & Wagner, 2017; Tramèr et al., 2017; Athalye et al., 2018) are repeatedly found that circumvent such defenses. To end this arm race, recent works (Wong & Kolter, 2018; Raghunathan et al., 2018; Wong et al., 2018; Wang et al., 2018) propose methods to certify examples to be robust against some specific norm-bounded adversarial perturbations for given inputs and to train models to optimize for certifiable robustness. However, all of the aforementioned methods aim at improving the overall robustness of the classifier. This means that the methods to improve robustness are designed to prevent seed examples in any class from being misclassified as any other classes. Achieving such a goal requires producing a perfect classifier, and has, unsurprisingly, remained elusive. Indeed, Mahloujifar et al. (2018) proved that if the metric probability space is concentrated, overall adversarial robustness is unattainable for any classifier with initial constant error. We argue that overall robustness may not be the appropriate criteria for measuring system performance in securitysensitive applications, since only certain kinds of adversarial misclassifications pose meaningful threats or provide value for adversaries.

The classic objective in a reinforcement learning (RL) problem is to find a policy that minimizes, in expectation, a long-run objective such as the infinite-horizon discounted or long-run average cost. In many practical applications, optimizing the expected value alone is not sufficient, and it may be necessary to include a risk measure in the optimization process, either as the objective or as a constraint. Various risk measures have been proposed in the literature, e.g., mean-variance tradeoff, exponential utility, the percentile performance, value at risk, conditional value at risk, prospect theory and its later enhancement, cumulative prospect theory. In this article, we focus on the combination of risk criteria and reinforcement learning in a constrained optimization framework, i.e., a setting where the goal to find a policy that optimizes the usual objective of infinite-horizon discounted/average cost, while ensuring that an explicit risk constraint is satisfied. We introduce the risk-constrained RL framework, cover popular risk measures based on variance, conditional value-at-risk and cumulative prospect theory, and present a template for a risk-sensitive RL algorithm. We survey some of our recent work on this topic, covering problems encompassing discounted cost, average cost, and stochastic shortest path settings, together with the aforementioned risk measures in a constrained framework. This non-exhaustive survey is aimed at giving a flavor of the challenges involved in solving a risk-sensitive RL problem, and outlining some potential future research directions.

As the technology is advancing, audio recognition in machine learning is improved as well. Research in audio recognition has traditionally focused on speech. Living creatures (especially the small ones) are part of the whole ecosystem, monitoring as well as maintaining them are important tasks. Species such as animals and birds are tending to change their activities as well as their habitats due to the adverse effects on the environment or due to other natural or man-made calamities. For those in far deserted areas, we will not have any idea about their existence until we can continuously monitor them. Continuous monitoring will take a lot of hard work and labor. If there is no continuous monitoring, then there might be instances where endangered species may encounter dangerous situations. The best way to monitor those species are through audio recognition. Classifying sound can be a difficult task even for humans. Powerful audio signals and their processing techniques make it possible to detect audio of various species. There might be many ways wherein audio recognition can be done. We can train machines either by pre-recorded audio files or by recording them live and detecting them. The audio of species can be detected by removing all the background noise and echoes. Smallest sound is considered as a syllable. Extracting various syllables is the process we are focusing on which is known as audio recognition in terms of Machine Learning (ML).

Understanding the uncertainty of a neural network's (NN) predictions is essential for many applications. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to the large number of parameters and data. Ensembling NNs provides a practical and scalable method for uncertainty quantification. Its drawback is that its justification is heuristic rather than Bayesian. In this work we propose one modification to the usual ensembling process, that does result in Bayesian behaviour: regularising parameters about values drawn from a prior distribution. Hence, we present an easily implementable, scalable technique for performing approximate Bayesian inference in NNs.

Implicit probabilistic models are models defined naturally in terms of a sampling procedure and often induces a likelihood function that cannot be expressed explicitly. We develop a simple method for estimating parameters in implicit models that does not require knowledge of the form of the likelihood function or any derived quantities, but can be shown to be equivalent to maximizing likelihood under some conditions. Our result holds in the non-asymptotic parametric setting, where both the capacity of the model and the number of data examples are finite. We also demonstrate encouraging experimental results.