We consider cooperative multi-agent consensus optimization problems over an undirected network of agents, where only those agents connected by an edge can directly communicate. The objective is to minimize the sum of agent-specific composite convex functions over agent-specific private conic constraint sets; hence, the optimal consensus decision should lie in the intersection of these private sets. We provide convergence rates in sub-optimality, infeasibility and consensus violation; examine the effect of underlying network topology on the convergence rates of the proposed decentralized algorithms; and show how to extend these methods to handle time-varying communication networks.

In this work we analyze the class prediction of parallel randomized ensembles by majority voting as an urn model. For a given test instance, the ensemble can be viewed as an urn of marbles of different colors. A marble represents an individual classifier. Its color represents the class label prediction of the corresponding classifier. The sequential querying of classifiers in the ensemble can be seen as draws without replacement from the urn. An analysis of this classical urn model based on the hypergeometric distribution makes it possible to estimate the confidence on the outcome of majority voting when only a fraction of the individual predictions is known. These estimates can be used to speed up the prediction by the ensemble. Specifically, the aggregation of votes can be halted when the confidence in the final prediction is sufficiently high. If one assumes a uniform prior for the distribution of possible votes the analysis is shown to be equivalent to a previous one based on Dirichlet distributions. The advantage of the current approach is that prior knowledge on the possible vote outcomes can be readily incorporated in a Bayesian framework. We show how incorporating this type of problem-specific knowledge into the statistical analysis of majority voting leads to faster classification by the ensemble and allows us to estimate the expected average speed-up beforehand.

Models for collecting and aggregating categorical data on crowdsourcing platforms typically fall into two broad categories: those assuming agents honest and consistent but with heterogeneous error rates, and those assuming agents strategic and seek to maximize their expected reward. The former often leads to tractable aggregation of elicited data, while the latter usually focuses on optimal elicitation and does not consider aggregation. In this paper, we develop a Bayesian model, wherein agents have differing quality of information, but also respond to incentives. Our model generalizes both categories and enables the joint exploration of optimal elicitation and aggregation. This model enables our exploration, both analytically and experimentally, of optimal aggregation of categorical data and optimal multiple-choice interface design.

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.

We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals in mind, such as achieving a certain strategic position. Conventional policy learning approaches, such as those based on Markov decision processes, generally fail at learning cohesive long-term behavior in such high-dimensional state spaces, and are only effective when fairly myopic decision-making yields the desired behavior. The key difficulty is that conventional models are ``single-scale'' and only learn a single state-action policy. We instead propose a hierarchical policy class that automatically reasons about both long-term and short-term goals, which we instantiate as a hierarchical neural network. We showcase our approach in a case study on learning to imitate demonstrated basketball trajectories, and show that it generates significantly more realistic trajectories compared to non-hierarchical baselines as judged by professional sports analysts.

For massive and heterogeneous modern data sets, it is of fundamental interest to provide guarantees on the accuracy of estimation when computational resources are limited. In the application of learning to rank, we provide a hierarchy of rank-breaking mechanisms ordered by the complexity in thus generated sketch of the data. This allows the number of data points collected to be gracefully traded off against computational resources available, while guaranteeing the desired level of accuracy. Theoretical guarantees on the proposed generalized rank-breaking implicitly provide such trade-offs, which can be explicitly characterized under certain canonical scenarios on the structure of the data.

The buzzwords "Industry 4.0" and "digital business" represent the start of a complex transformational process that will deeply affect industry and society during the next decade. This transformation is based on the convergence of the real (analog) world and the virtual (digital) world by means of machineto- machine (M2M) communication, autonomous systems (for example, robotics) and the Internet of Things (IoT). The German government uses the term "Industry 4.0" as the title of a government project promoting the computerization of traditional industries and the creation of intelligent factories (smart factories) that will be supported by cyberphysical systems and the IoT. The digits "4.0" in Industry 4.0 stand for the fourth industrial revolution: the transition of production from digital processing to fully interconnected processes, products and services. It follows the evolution of production processes for tradable goods from manufacturing to industry production (the first revolution), the move from steam-driven machine production to electricity-driven production (the second revolution) and the shift from analog processing to digital processing and microelectronics (the third revolution). One of the major features of Industry 4.0 is the ability of machines and devices to communicate with each other without a human interface.

Distributed constraint optimization problems enable the representation of many combinatorial problems that are distributed by nature. An important motivation for such problems is to preserve the privacy of the participating agents during the solving process. The present paper introduces a novel privacy-preserving branch and bound algorithm for this purpose. The proposed algorithm, P-SyncBB, preserves constraint, topology and decision privacy. The algorithm requires secure solutions to several multi-party computation problems. Consequently, appropriate novel secure protocols are devised and analyzed. An extensive experimental evaluation on different benchmarks, problem sizes, and constraint densities shows that P-SyncBB exhibits superior performance to other privacy-preserving complete DCOP algorithms.

International travelers could soon be greeted by lie-detecting robot kiosks before crossing the border. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists. The robot uses eye-detection software along with an array of sensors to pick up on the physiological signs that indicate a person is lying, and once it becomes suspicious, it can flag the passenger for further inspection. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists Once a traveler steps up to the kiosk, they will be asked a series of questions, such as: 'Do you have fruits or vegetables in your luggage?' or'Are you carrying any weapons with you?' While this is happening, AVATAR uses eye-detection software and motion and pressure sensors to track any signs of lying or discomfort. To separate the liars from those who are just nervous about flying, it will also ask a number of innocuous baseline questions.

International travelers could soon be greeted by lie-detecting robot kiosks before crossing the border. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists. The robot uses eye-detection software along with an array of sensors to pick up on the physiological signs that indicate a person is lying, and once it becomes suspicious, it can flag the passenger for further inspection. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists Once a traveler steps up to the kiosk, they will be asked a series of questions, such as: 'Do you have fruits or vegetables in your luggage?' or'Are you carrying any weapons with you?' While this is happening, AVATAR uses eye-detection software and motion and pressure sensors to track any signs of lying or discomfort. To separate the liars from those who are just nervous about flying, it will also ask a number of innocuous baseline questions.