Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation. However, addressing this problem has two critical challenges: (i) Measuring the multi-marginal distance among different domains is very intractable; (ii) It is very difficult to exploit cross-domain correlations to match the target domain distributions. In this paper, we propose a novel Multi-marginal Wasserstein GAN (MWGAN) to minimize Wasserstein distance among domains. Specifically, with the help of multi-marginal optimal transport theory, we develop a new adversarial objective function with inner- and inter-domain constraints to exploit cross-domain correlations. Moreover, we theoretically analyze the generalization performance of MWGAN, and empirically evaluate it on the balanced and imbalanced translation tasks. Extensive experiments on toy and real-world datasets demonstrate the effectiveness of MWGAN.

A BSTRACT This paper is concerned with the defense of deep models against adversarial attacks. We develop an adversarial detection method, which is inspired by the certificate defense approach, and captures the idea of separating class clusters in the embedding space to increase the margin. The resulting defense is intuitive, effective, scalable, and can be integrated into any given neural classification model. Our method demonstrates state-of-the-art (detection) performance under all threat models. 1 Introduction Defending machine learning models from adversarial attacks has become an increasingly pressing issue as deep neural networks become associated with more critical aspects of society. Adversarial attacks can effectively fool deep models and force them to misclassify, using a slight but maliciously-designed distortion that is typically invisible to the human eye (Carlini & Wagner, 2017c; Athalye et al., 2018). Despite numerous developments, defense mechanisms are still wanting. Many interesting ideas have been proposed to construct defense mechanisms for adversarial examples. Among these are adversarial training (Metzen et al., 2017; Zuo et al., 2020; Y an et al., 2018), ensemble methods (Strauss et al., 2017), and randomization (Dhillon et al., 2018; Xu et al., 2017) to name a few.

For many applications it is critical to know the uncertainty of a neural network's predictions. While a variety of neural network parameter estimation methods have been proposed for uncertainty estimation, they have not been rigorously compared across uncertainty measures. We assess four of these parameter estimation methods to calibrate uncertainty estimation using four different uncertainty measures: entropy, mutual information, aleatoric uncertainty and epistemic uncertainty. We also evaluate their calibration using expected calibration error. We additionally propose a novel method of neural network parameter estimation called RECAST, which combines cosine annealing with warm restarts with Stochastic Gradient Langevin Dynamics, capturing more diverse parameter distributions. When benchmarked against mutilated data from MNIST, we show that RECAST is well-calibrated and when combined with predictive entropy and epistemic uncertainty it offers the best calibrated measure of uncertainty when compared to recent methods.

Deep Neural Networks (DNN) applications are increasingly being deployed in always-on IoT devices. However, the limited resources in tiny microcontroller units (MCUs) limit the deployment of the required Machine Learning (ML) models. Therefore alternatives to traditional architectures such as Computation-In-Memory based on resistive nonvolatile memories (NVM), promising high integration density, low power consumption and massively-parallel computation capabilities, are under study. However, these technologies are still immature and suffer from intrinsic analog nature problems --noise, non-linearities, inability to represent negative values, and limited-precision per device. Consequently, mapping DNNs to NVM crossbars requires the full-custom design of each one of the DNN layers, involving finely tuned blocks such as ADC/DACs or current subtractors/adders, and thus limiting the chip reconfigurability. This paper presents an NVM-aware framework to efficiently train and map the DNN to the NVM hardware. We propose the first method that trains the NN weights while ensuring uniformity across layer weights/activations, improving HW blocks re-usability. Firstly, this quantization algorithm obtains uniform scaling across the DNN layers independently of their characteristics, removing the need of per-layer full-custom design while reducing the peripheral HW. Secondly, for certain applications we make use of Network Architecture Search, to avoid using negative weights. Unipolar weight matrices translate into simpler analog periphery and lead to $67 \%$ area improvement and up to $40 \%$ power reduction. We validate our idea with CIFAR10 and HAR applications by mapping to crossbars using $4$-bit and $2$-bit devices. Up to $92.91\%$ accuracy ($95\%$ floating-point) can be achieved using $2$-bit only-positive weights for HAR.

We discuss the objectives of automation equipped with non-trivial decision making, or creating artificial intelligence, in the financial markets and provide a possible alternative. Intelligence might be an unintended consequence of curiosity left to roam free, best exemplified by a frolicking infant. For this unintentional yet welcome aftereffect to set in a foundational list of guiding principles needs to be present. A consideration of these requirements allows us to propose a test of intelligence for trading programs, on the lines of the Turing Test, long the benchmark for intelligent machines. We discuss the application of this methodology to the dilemma in finance, which is whether, when and how much to Buy, Sell or Hold.

Making decisions in the presence of a strategic opponent requires one to take into account the opponent's ability to actively mask its intended objective. To describe such strategic situations, we introduce the non-cooperative inverse reinforcement learning (N-CIRL) formalism. The N-CIRL formalism consists of two agents with completely misaligned objectives, where only one of the agents knows the true objective function. Formally, we model the N-CIRL formalism as a zero-sum Markov game with one-sided incomplete information. Through interacting with the more informed player, the less informed player attempts to both infer, and act according to, the true objective function. As a result of the one-sided incomplete information, the multi-stage game can be decomposed into a sequence of single-stage games expressed by a recursive formula. Solving this recursive formula yields the value of the N-CIRL game and the more informed player's equilibrium strategy. Another recursive formula, constructed by forming an auxiliary game, termed the dual game, yields the less informed player's strategy. Building upon these two recursive formulas, we develop a computationally tractable algorithm to approximately solve for the equilibrium strategies. Finally, we demonstrate the benefits of our N-CIRL formalism over the existing multi-agent IRL formalism via extensive numerical simulation in a novel cyber security setting.

Prec ision Medicine (PM) is an emerging approach that appears with the impression of changing the existing paradigm of medical practice. Recent advances in technological innovations and genetics, and the growing availability of health data have set a new pace o f the research and imposes a set of new requirements on different stakeholders. To date, some studies are available that discuss about different aspects of PM. Nevertheless, a holistic representation of those aspects deemed to confer the technological pers pective, in relation to applications and challenges, is mostly ignored. In this context, this paper surveys advances in PM from informatics viewpoint and reviews the enabling tools and techniques in a categorized manner. In addition, the study discusses ho w other technological paradigms including big data, artificial intelligence, and internet of things can be exploited to advance the potentials of PM. Furthermore, the paper provides some guidelines for future research for seamless implementation and wide - s cale deployment of PM based on identified open issues and associated challenges. To this end, the paper proposes an integrated holistic framework for PM motivating informatics researchers to design their relevant research works in an appropriate context.

XDeep is an open-source Python package developed to interpret deep models for both practitioners and researchers. Overall, XDeep takes a trained deep neural network (DNN) as the input, and generates relevant interpretations as the output with the post-hoc manner. From the functionality perspective, XDeep integrates a wide range of interpretation algorithms from the state-of-the-arts, covering different types of methodologies, and is capable of providing both local explanation and global explanation for DNN when interpreting model behaviours. With the well-documented API designed in XDeep, end-users can easily obtain the interpretations for their deep models at hand with several lines of codes, and compare the results among different algorithms. XDeep is generally compatible with Python 3, and can be installed through Python Package Index (PyPI). The source codes are available at: https://github.com/datamllab/xdeep.

Learning contact-rich, robotic manipulation skills is a challenging problem due to the high-dimensionality of the state and action space as well as uncertainty from noisy sensors and inaccurate motor control. To combat these factors and achieve more robust manipulation, humans actively exploit contact constraints in the environment. By adopting a similar strategy, robots can also achieve more robust manipulation. In this paper, we enable a robot to autonomously modify its environment and thereby discover how to ease manipulation skill learning. Specifically, we provide the robot with fixtures that it can freely place within the environment. These fixtures provide hard constraints that limit the outcome of robot actions. Thereby, they funnel uncertainty from perception and motor control and scaffold manipulation skill learning. We propose a learning system that consists of two learning loops. In the outer loop, the robot positions the fixture in the workspace. In the inner loop, the robot learns a manipulation skill and after a fixed number of episodes, returns the reward to the outer loop. Thereby, the robot is incentivised to place the fixture such that the inner loop quickly achieves a high reward. We demonstrate our framework both in simulation and in the real world on three tasks: peg insertion, wrench manipulation and shallow-depth insertion. We show that manipulation skill learning is dramatically sped up through this way of scaffolding.

In order to make good decision under uncertainty an agent must learn from observations. To do so, two of the most common frameworks are Contextual Bandits and Markov Decision Processes (MDPs). In this paper, we study whether there exist algorithms for the more general framework (MDP) which automatically provide the best performance bounds for the specific problem at hand without user intervention and without modifying the algorithm. In particular, it is found that a very minor variant of a recently proposed reinforcement learning algorithm for MDPs already matches the best possible regret bound $\tilde O (\sqrt{SAT})$ in the dominant term if deployed on a tabular Contextual Bandit problem despite the agent being agnostic to such setting.