Distributed Constraint Optimization Problems (DCOPs) can be optimally solved by distributed search algorithms, such as ADOPT and BnB-ADOPT. In centralized solving, maintaining soft arc consistency during search has proved to be beneficial for performance. In this thesis we aim to explore the maintenance of different levels of soft arc consistency in distributed search when solving DCOPs.

Heuristic search is a central component of many important applications in AI including automated planning.  While we can find  optimal solutions to heuristic search problems, doing so may take hours or days. For practical applications, this is unacceptably slow, and we must rely on algorithms which find solutions of high, but not optimal, quality or ones which bound the time used directly. In my dissertation, I present and analyze algorithms for the following settings: quality bounded heuristic search and time  bounded heuristic search. The central theme of my doctoral work will be that taking advantage of additional information can improve the performance of heuristic search algorithms.

We study the relationship between optimal planning algorithms, in the form of (iterative deepening) A* with (forward) state-space search, and the reduction of the problem to SAT. Our results establish a strict dominance relation between the two approaches: any iterative deepening A* search can be efficiently simulated in the SAT framework, assuming that the heuristic has been encoded in the SAT problem, but the opposite is not possible as A* and IDA* searches sometimes take exponentially longer.

In binary-utility games, an agent can have only two possible utility values for final states, 1 (win) and 0 (lose). An adversarial binaryutility game is one where for each final state there must be at least one winning and one losing agent. We define an unbiased rational agent as one that seeks to maximize its utility value, but is equally likely to choose between states with the same utility value. This induces a probability distribution over the outcomes of the game, from which an agent can infer its probability to win. A single adversary binary game is one where there are only two possible outcomes, so that the winning probabilities remain binary values. In this case, the rational action for an agent is to play minimax. In this work we focus on the more complex, multiple-adversary environment. We propose a new algorithmic framework where agents try to maximize their winning probabilities. We begin by theoretically analyzing why an unbiased rational agent should take our approach in an unbounded environment and not that of the existing Paranoid or MaxN algorithms. We then expand our framework to a resource-bounded environment, where winning probabilities are estimated, and show empirical results supporting our claims.

There are a number of papers that use hill-climbing or k-We introduce a new nearest neighbor search algorithm. NN graphs for nearest neighbor search, but to the best of our The algorithm builds a nearest neighbor knowledge, using hill-climbing on k-NN graphs is a new idea.

The Partner Units Problem is a specific type of configuration problem with important applications in the area of surveillance and security. In this work we show that a special case of the problem, that is of great interest to our partners in industry, can directly be tackled via a structural problem decompostion method. Combining these theoretical insights with general purpose AI techniques such as constraint satisfaction and SAT solving proves to be particularly effective in practice.

We develop a general framework for social choice problems in which a limited number of alternatives can be recommended to an agent population. In our budgeted social choice model, this limit is determined by a budget, capturing problems that arise naturally in a variety of contexts, and spanning the continuum from pure consensus decision making (i.e., standard social choice) to fully personalized recommendation. Our approach applies a form of segmentation to social choice problems— requiring the selection of diverse options tailored to different agent types—and generalizes certain multi-winner election schemes. We show that standard rank aggregation methods perform poorly, and that optimization in our model is NP-complete; but we develop fast greedy algorithms with some theoretical guarantees. Experiments on real-world datasets demonstrate the effectiveness of our algorithms.

In this paper, we address the problem of learning the structure of a pairwise graphical model from samples in a high-dimensional setting. Our first main result studies the sparsistency, or consistency in sparsity pattern recovery, properties of a forward-backward greedy algorithm as applied to general statistical models. As a special case, we then apply this algorithm to learn the structure of a discrete graphical model via neighborhood estimation. As a corollary of our general result, we derive sufficient conditions on the number of samples n, the maximum node-degree d and the problem size p, as well as other conditions on the model parameters, so that the algorithm recovers all the edges with high probability. Our result guarantees graph selection for samples scaling as n = Omega(d^2 log(p)), in contrast to existing convex-optimization based algorithms that require a sample complexity of \Omega(d^3 log(p)). Further, the greedy algorithm only requires a restricted strong convexity condition which is typically milder than irrepresentability assumptions. We corroborate these results using numerical simulations at the end.

In this paper, we give a new sharp generalization bound of lp-MKL which is a generalized framework of multiple kernel learning (MKL) and imposes lp-mixed-norm regularization instead of l1-mixed-norm regularization. We utilize localization techniques to obtain the sharp learning rate. The bound is characterized by the decay rate of the eigenvalues of the associated kernels. A larger decay rate gives a faster convergence rate. Furthermore, we give the minimax learning rate on the ball characterized by lp-mixed-norm in the product space. Then we show that our derived learning rate of lp-MKL achieves the minimax optimal rate on the lp-mixed-norm ball.

Cancer kills millions of people each year. From an AI perspective, finding effective treatments for cancer is a high-dimensional search problem characterized by many molecularly distinct cancer subtypes, many potential targets and drug combinations, and a dearth of high quality data to connect molecular subtypes and treatments to responses. The broadening availability of molecular diagnostics and electronic medical records, presents both opportunities and challenges to apply AI techniques to personalize and improve cancer treatment. We discuss these in the context of Cancer Commons, a “rapid learning” community where patients, physicians, and researchers collect and analyze the molecular and clinical data from every cancer patient, and use these results to individualize therapies. Research opportunities include: adaptively-planning and executing individual treatment experiments across the whole patient population, inferring the causal mechanisms of tumors, predicting drug response in individuals, and generalizing these findings to new cases. The goal is to treat each patient in accord with the best available knowledge, and to continually update that knowledge to benefit subsequent patients. Achieving this goal is a worthy grand challenge for AI.