The question of aggregating pair-wise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g. MSR's TrueSkill system) and chess players, aggregating social opinions, or deciding which product to sell based on transactions. In most settings, in addition to obtaining a ranking, finding `scores' for each object (e.g. player's rating) is of interest for understanding the intensity of the preferences. In this paper, we propose Rank Centrality, an iterative rank aggregation algorithm for discovering scores for objects (or items) from pair-wise comparisons. The algorithm has a natural random walk interpretation over the graph of objects with an edge present between a pair of objects if they are compared; the score, which we call Rank Centrality, of an object turns out to be its stationary probability under this random walk. To study the efficacy of the algorithm, we consider the popular Bradley-Terry-Luce (BTL) model (equivalent to the Multinomial Logit (MNL) for pair-wise comparisons) in which each object has an associated score which determines the probabilistic outcomes of pair-wise comparisons between objects. In terms of the pair-wise marginal probabilities, which is the main subject of this paper, the MNL model and the BTL model are identical. We bound the finite sample error rates between the scores assumed by the BTL model and those estimated by our algorithm. In particular, the number of samples required to learn the score well with high probability depends on the structure of the comparison graph. When the Laplacian of the comparison graph has a strictly positive spectral gap, e.g. each item is compared to a subset of randomly chosen items, this leads to dependence on the number of samples that is nearly order-optimal.

Answering conjunctive queries over ontology-enriched datasets is a core reasoning task for many applications. Query answering is, however, computationally very expensive, which has led to the development of query answering procedures that sacrifice either expressive power of the ontology language, or the completeness of query answers in order to improve scalability. In this paper, we describe a hybrid approach to query answering over OWL 2 ontologies that combines a datalog reasoner with a fully-fledged OWL 2 reasoner in order to provide scalable `pay-as-you-go' performance. The key feature of our approach is that it delegates the bulk of the computation to the datalog reasoner and resorts to expensive OWL 2 reasoning only as necessary to fully answer the query. Furthermore, although our main goal is to efficiently answer queries over OWL 2 ontologies and data, our technical results are very general and our approach is applicable to first-order knowledge representation languages that can be captured by rules allowing for existential quantification and disjunction in the head; our only assumption is the availability of a datalog reasoner and a fully-fledged reasoner for the language of interest, both of which are used as `black boxes'. We have implemented our techniques in the PAGOdA system, which combines the datalog reasoner RDFox and the OWL 2 reasoner HermiT. Our extensive evaluation shows that PAGOdA succeeds in providing scalable pay-as-you-go query answering for a wide range of OWL 2 ontologies, datasets and queries.

Latent factor models are the canonical statistical tool for exploratory analyses of low-dimensional linear structure for an observation matrix with p features across n samples. We develop a structured Bayesian group factor analysis model that extends the factor model to multiple coupled observation matrices; in the case of two observations, this reduces to a Bayesian model of canonical correlation analysis. The main contribution of this work is to carefully define a structured Bayesian prior that encourages both element-wise and column-wise shrinkage and leads to desirable behavior on high-dimensional data. In particular, our model puts a structured prior on the joint factor loading matrix, regularizing at three levels, which enables element-wise sparsity and unsupervised recovery of latent factors corresponding to structured variance across arbitrary subsets of the observations. In addition, our structured prior allows for both dense and sparse latent factors so that covariation among either all features or only a subset of features can both be recovered. We use fast parameter-expanded expectation-maximization for parameter estimation in this model. We validate our method on both simulated data with substantial structure and real data, comparing against a number of state-of-the-art approaches. These results illustrate useful properties of our model, including i) recovering sparse signal in the presence of dense effects; ii) the ability to scale naturally to large numbers of observations; iii) flexible observation- and factor-specific regularization to recover factors with a wide variety of sparsity levels and percentage of variance explained; and iv) tractable inference that scales to modern genomic and document data sizes.

There are two main different setups for statistical learning: centralized learning and distributed learning. In the centralized learning, which has been studied extensively, all data is available at a centralized location. In the distributed learning, data is stored in multiple terminals. The distributed learning setup has attracted significant recent research interests as the data involved in learning is increasingly large in volume and might be stored in multiple terminals [1], [2], [3], [4]. For the distributed learning, each terminal either has a few observations about all variables, or has full knowledge about a subset of variables (all observations about a subset of variables). The first scenario is relatively easier since each terminal can still make its own local inference without even communicating with each other, while communication between terminals is essential for the second scenario. In this paper, we focus on the more challenging second scenario. In particular, we consider a distributed parameter estimation problem.

When to make a decision is a key question in decision making problems characterized by uncertainty. In this paper we deal with decision making in environments where information arrives dynamically. We address the tradeoff between waiting and stopping strategies. On the one hand, waiting to obtain more information reduces uncertainty, but it comes with a cost. Stopping and making a decision based on an expected utility reduces the cost of waiting, but the decision is based on uncertain information. We propose an optimal algorithm and two approximation algorithms. We prove that one approximation is optimistic - waits at least as long as the optimal algorithm, while the other is pessimistic - stops not later than the optimal algorithm. We evaluate our algorithms theoretically and empirically and show that the quality of the decision in both approximations is near-optimal and much faster than the optimal algorithm. Also, we can conclude from the experiments that the cost function is a key factor to chose the most effective algorithm.

Socially Assistive Robotics (SAR) is a growing field dedicated to developing models and algorithms that enable robots to help people achieve goals through social interaction (Feil-Seifer and Mataric 2005). Prior work in this field has focused on one-on-one interactions, but there is interest in extending this work to multi-party interactions. We contribute to the study of multi-party SAR by defining the role of moderator, an agent that is responsible for directing an interaction, but is not necessarily directly participating in the task. We present a computational formalization of the task of moderation as the process by which a goal-directed multi-party interaction is regulated via manipulation of interaction resources, including both physical resources, such as an object or a tool, and social resources, such as the conversational floor or participants' attention. Finally, we present preliminary results of an analysis of self-moderated multi-party human-human interaction that support several of the underlying assumptions of this formalization.

Video-game designers often tessellate continuous 2-dimensional terrain into a grid of blocked and unblocked square cells. The three main ways to calculate short paths on such a grid are to determine truly shortest paths, shortest vertex paths and shortest grid paths, listed here in decreasing  order of computation time and increasing order of resulting path length. We show that, for both vertex and grid paths on both 4-neighbor and 8-neighbor grids, placing vertices at cell corners rather than at cell centers tends to result in shorter paths. We quantify the advantage of cell corners over cell centers theoretically with tight worst-case bounds on the ratios of path lengths, and empirically on a large set of benchmark test cases. We also quantify the advantage of 8-neighbor grids over 4-neighbor grids.

This paper analyzes repeated multimarket contact with observation errors where two players operate in multiple markets simultaneously. Multimarket contact has received much attention from the literature of economics,management, and information systems. Despite vast empirical studies that examine whether multimarket contact fosters cooperation/collusion, little is theoretically known as to how players behave in an equilibrium when each player receives a noisy observation of other firms’ actions. This paper tackles an essentially realistic situation where the players do not share common information; each player may observe a different signal (private monitoring). Thus, players have difficulty in having a common understanding about which market their opponent should be punished in and when punishment should be started and ended. We first theoretically show that an extension of 1-period mutual punishment (1MP) for an arbitrary number of markets can be an equilibrium. Second, by applying a verification method, we identify a simple equilibrium strategy called "locally cautioning (LC)" that restores collusion after observation error or deviation. We then numerically reveal that LC significantly outperforms 1MP and achieves the highest degree of collusion.

This study focuses on the question: "What are the computational formalisms at the heart of deceptive and counter-deceptive machines?" We formulate deception using a dynamic epistemic logic. Three different types of deception are considered: deception by lying, deception by bluffing and deception by truth-telling, depending on whether a speaker believes what he/she says or not. Next we consider various situations where an act of deceiving happens. Intentional deception is accompanied by a speaker's intent to deceive. Indirect deception happens when false information is carried over from person to person. Self-deception is an act of deceiving the self. We investigate formal properties of different sorts of deception.

Cinematic, Ambient, Inhabitable Narrative Environments (CAINEs) are conceptual AI-driven interactive story systems combining text, audio, and visual imagery that are scalable and adaptable to a wide range of storytelling needs and interactor inputs. Conceived by at artist outside the AI community, they represent an opportunity to use AI in a nontraditional and immersive narrative fashion that relies not on the goal-based arrangement of story elements, but on the accretion and association of those elements in the minds of interactors. This paper represents the initial phase of the project’s development.