Modeling the purposeful behavior of imperfect agents from a small number of observations is a challenging task. When restricted to the single-agent decision-theoretic setting, inverse optimal control techniques assume that observed behavior is an approximately optimal solution to an unknown decision problem. These techniques learn a utility function that explains the example behavior and can then be used to accurately predict or imitate future behavior in similar observed or unobserved situations. In this work, we consider similar tasks in competitive and cooperative multi-agent domains. Here, unlike single-agent settings, a player cannot myopically maximize its reward; it must speculate on how the other agents may act to influence the game's outcome. Employing the game-theoretic notion of regret and the principle of maximum entropy, we introduce a technique for predicting and generalizing behavior.

As large-scale theft of data from corporate servers is becoming increasingly common, it becomes interesting to examine alternatives to the paradigm of centralizing sensitive data into large databases. Instead, one could use cryptography and distributed computation so that sensitive data can be supplied and processed in encrypted form, and only the final result is made known. In this paper, we examine how such a paradigm can be used to implement constraint satisfaction, a technique that can solve a broad class of AI problems such as resource allocation, planning, scheduling, and diagnosis. Most previous work on privacy in constraint satisfaction only attempted to protect specific types of information, in particular the feasibility of particular combinations of decisions. We formalize and extend these restricted notions of privacy by introducing four types of private information, including the feasibility of decisions and the final decisions made, but also the identities of the participants and the topology of the problem. We present distributed algorithms that allow computing solutions to constraint satisfaction problems while maintaining these four types of privacy. We formally prove the privacy properties of these algorithms, and show experiments that compare their respective performance on benchmark problems.

This paper advances a framework for modeling the component interactions between cognitive and social aspects of scientific creativity and technological innovation. Specifically, it aims to characterize Innovation Networks; those networks that involve the interplay of people, ideas and organizations to create new, technologically feasible, commercially-realizable products, processes and organizational structures. The tri-partite framework captures networks of ideas (Concept Level), people (Individual Level) and social structures (Social-Organizational Level) and the interactions between these levels. At the concept level, new ideas are the nodes that are created and linked, kept open for further investigation or closed if solved by actors at the individual or organizational levels. At the individual level, the nodes are actors linked by shared worldviews (based on shared professional, educational, experiential backgrounds) who are the builders of the concept level. At the social-organizational level, the nodes are organizations linked by common efforts on a given project (e.g., a company-university collaboration) that by virtue of their intellectual property or rules of governance constrain the actions of individuals (at the Individual Level) or ideas (at the Concept Level). After describing this framework and its implications we paint a number of scenarios to flesh out how it can be applied.

This paper presents a supervised bayesian approach to model expertise in online forums with application to question routing. The proposed method extends the well-known sLDA model to the multi-task case, accounting for a supervised stage with multiple outputs per document corresponding to the users of the system. A study of the characteristics of real world data revealed a number of challenges in the practical application of this model, relevant to the research community.

Although the social medium Twitter grants users freedom of speech, its instantaneous nature and retweeting features also amplify hate speech. Because Twitter has a sizeable black constituency, racist tweets against blacks are especially detrimental in the Twitter community, though this effect may not be obvious against a backdrop of half a billion tweets a day.1 We apply a supervised machine learning approach, employing inexpensively acquired labeled data from diverse Twitter accounts to learn a binary classifier for the labels “racist” and “nonracist.” The classifier has a 76% average accuracy on individual tweets, suggesting that with further improvements, our work can contribute data on the sources of anti-black hate speech.

We consider judgment aggregation over multiple independent issues, where the chairperson has her own opinion, and can try to bias the outcome by bundling several issues together. Since for each bundle judges must give a uniform answer on all issues, different partitions of the issues may result in an outcome that significantly differs from the "true," issue-wise, decision. We prove that the bundling problem faced by the chairperson, i.e. trying to bias the outcome towards her own opinion, is computationally difficult in the worst case. Then we study the probability that an effective bundling attack exists as the disparity between the opinions of the judges and the chair varies. We show that if every judge initially agrees with the chair on every issue with probability of at least 1/2, then there is almost always a bundling attack (i.e. a partition) where the opinion of the chair on all issues is approved. Moreover, such a partition can be found efficiently. In contrast, when the probability is lower than 1/2 then the chair cannot force her opinion using bundling even on a single issue.

We introduce Supersparse Linear Integer Models (SLIM) as a tool to create scoring systems for binary classification. We derive theoretical bounds on the true risk of SLIM scoring systems, and present experimental results to show that SLIM scoring systems are accurate, sparse, and interpretable classification models.

Machine Learning (ML) algorithms are used to train computers to perform a variety of complex tasks and improve with experience. Computers learn how to recognize patterns, make unintended decisions, or react to a dynamic environment. Certain trained machines may be more effective than others because they are based on more suitable ML algorithms or because they were trained through superior training sets. Although ML algorithms are known and publicly released, training sets may not be reasonably ascertainable and, indeed, may be guarded as trade secrets. While much research has been performed about the privacy of the elements of training sets, in this paper we focus our attention on ML classifiers and on the statistical information that can be unconsciously or maliciously revealed from them. We show that it is possible to infer unexpected but useful information from ML classifiers. In particular, we build a novel meta-classifier and train it to hack other classifiers, obtaining meaningful information about their training sets. This kind of information leakage can be exploited, for example, by a vendor to build more effective classifiers or to simply acquire trade secrets from a competitor's apparatus, potentially violating its intellectual property rights.

Rule based reasoning (RBR) and case based reasoning (CBR) have emerged as two important and complementary reasoning methodologies in artificial intelligence (Al). For problem solving in complex, real world situations, it is useful to integrate RBR and CBR. This paper presents an approach to achieve a compact and seamless integration of RBR and CBR within the base architecture of rules. The paper focuses on the possibilistic nature of the approximate reasoning methodology common to both CBR and RBR. In CBR, the concept of similarity is casted as the complement of the distance between cases. In RBR the transitivity of similarity is the basis for the approximate deductions based on the generalized modus ponens. It is shown that the integration of CBR and RBR is possible without altering the inference engine of RBR. This integration is illustrated in the financial domain of mergers and acquisitions. These ideas have been implemented in a prototype system called MARS.

A scientific reasoning system makes decisions using objective evidence in the form of independent experimental trials, propositional axioms, and constraints on the probabilities of events. As a first step towards this goal, we propose a system that derives probability intervals from objective evidence in those forms. Our reasoning system can manage uncertainty about data and rules in a rule based expert system. We expect that our system will be particularly applicable to diagnosis and analysis in domains with a wealth of experimental evidence such as medicine. We discuss limitations of this solution and propose future directions for this research. This work can be considered a generalization of Nilsson's "probabilistic logic" [Nil86] to intervals and experimental observations.