Officers of the Florida AI Research Society.

Special tracks are a vital part of the FLAIRS Thanks go to the authors of both accepted and rejected conferences, with 11 held at FLAIRS-25. Over 90 papers; the special track coordinator Chutima percent of the papers were reviewed by four or Boonthum-Denecke and all the special track organizers; more reviewers, and all papers were reviewed by at the program committees and their reviewers; least three. These were coordinated by the program the invited speakers; Chad Lane for organizing committees of the general conference and the special the conference; Jean Gerber for administering the tracks. The accepted submissions include 74 conference; the Florida Artificial International Research full papers (19 from the general conference and 55 Society for maintaining the conference series; from the special tracks), 27 short papers presented the Association for the Advancement of Artificial as posters (6 from the general conference and 21 Intelligence for its cooperation with the conference; from the special tracks), and 20 poster abstracts Mike Hamilton for organizing the publication that appear in these proceedings. of the proceedings; and EasyChair for hosting the review process. The program included five invited talks: Bill Swartout, the Director of Technology and Research Professor at the University of Southern California's

This work discusses the problem of sparse signal recovery when there is correlation among the values of non-zero entries. We examine intra-vector correlation in the context of the block sparse model and inter-vector correlation in the context of the multiple measurement vector model, as well as their combination. Algorithms based on the sparse Bayesian learning are presented and the benefits of incorporating correlation at the algorithm level are discussed. The impact of correlation on the limits of support recovery is also discussed highlighting the different impact intra-vector and inter-vector correlations have on such limits.

The regularization path of the Lasso can be shown to be piecewise linear, making it possible to "follow" and explicitly compute the entire path. We analyze in this paper this popular strategy, and prove that its worst case complexity is exponential in the number of variables. We then oppose this pessimistic result to an (optimistic) approximate analysis: We show that an approximate path with at most O(1/sqrt(epsilon)) linear segments can always be obtained, where every point on the path is guaranteed to be optimal up to a relative epsilon-duality gap. We complete our theoretical analysis with a practical algorithm to compute these approximate paths.

Interpreting neural spike trains, compressing video, identifying features in DNA microarrays, and recognizing particles in high energy physics all rely upon the ability to find and model complex structure in a high dimensional space. Despite their great promise, high dimensional probabilistic models are frequently computationally intractable to work with in practice. In this thesis I develop solutions to overcome this intractability, primarily in the context of energy based models. A common cause of intractability is that model distributions cannot be analytically normalized. Probabilities can only be computed up to a constant, making training exceedingly difficult. To solve this problem I propose'minimum probability flow learning', a variational technique for parameter estimation in such models.

In this paper we describe COLIN, a forward-chaining heuristic search planner, capable of reasoning with COntinuous LINear numeric change, in addition to the full temporal semantics of PDDL. Through this work we make two advances to the state-of-the-art in terms of expressive reasoning capabilities of planners: the handling of continuous linear change, and the handling of duration-dependent effects in combination with duration inequalities, both of which require tightly coupled temporal and numeric reasoning during planning. COLIN combines FF-style forward chaining search, with the use of a Linear Program (LP) to check the consistency of the interacting temporal and numeric constraints at each state. The LP is used to compute bounds on the values of variables in each state, reducing the range of actions that need to be considered for application. In addition, we develop an extension of the Temporal Relaxed Planning Graph heuristic of CRIKEY3, to support reasoning directly with continuous change. We extend the range of task variables considered to be suitable candidates for specifying the gradient of the continuous numeric change effected by an action. Finally, we explore the potential for employing mixed integer programming as a tool for optimising the timestamps of the actions in the plan, once a solution has been found. To support this, we further contribute a selection of extended benchmark domains that include continuous numeric effects. We present results for COLIN that demonstrate its scalability on a range of benchmarks, and compare to existing state-of-the-art planners.

Covariance graphical lasso applies a lasso penalty on the elements of the covariance matrix. This method is useful because it not only produces sparse estimation of covariance matrix but also discovers marginal independence structures by generating zeros in the covariance matrix. We propose and explore two new algorithms for solving the covariance graphical lasso problem. Our new algorithms are based on coordinate descent and ECM. We show that these two algorithms are more attractive than the only existing competing algorithm of Bien and Tibshirani (2011) in terms of simplicity, speed and stability. We also discuss convergence properties of our algorithms.

For successful experimental implementation of any quantum protocol, the quantum states and operations involved must be confirmed to be sufficiently closed to their theoretical targets. One way to obtain such a confirmation is to perform another experiment and from the obtained data make an estimate of the quantum operator involved. Statistically, this is a constrained multiparameter estimation problem - the quantum estimation problem - where we assume we are given a finite number of identical copies of a quantum state or operation, we perform measurements whose mathematical description is assumed to be known, and from the outcome statistics we make our estimate. Due to the probabilistic behavior of the measurement outcomes and the finiteness of the number of measurement trials, there always exist statistical errors in any quantum estimate. The size of the error depends on the choice of measurements and the estimation procedure. In statistics, the former is called an experimental design, while the latter is called an estimator. It is, therefore, a key aim of both classical and quantum estimation theory to find a combination of experimental design and estimator which gives us more precise estimation results using fewer measurement trials. A standard combination in quantum information experiments is that of quantum tomography and maximum likelihood estimator. Although the term "quantum tomography" can be used in several different contexts, we use it to mean an experimental design in which an independently and identically prepared set of measurements are used throughout the entire experiment [1].

The free energy functional has recently been proposed as a variational principle for bounded rational decision-making, since it instantiates a natural trade-off between utility gains and information processing costs that can be axiomatically derived. Here we apply the free energy principle to general decision trees that include both adversarial and stochastic environments. We derive generalized sequential optimality equations that not only include the Bellman optimality equations as a limit case, but also lead to well-known decision-rules such as Expectimax, Minimax and Expectiminimax. We show how these decision-rules can be derived from a single free energy principle that assigns a resource parameter to each node in the decision tree. These resource parameters express a concrete computational cost that can be measured as the amount of samples that are needed from the distribution that belongs to each node. The free energy principle therefore provides the normative basis for generalized optimality equations that account for both adversarial and stochastic environments.

This research is about the distribution of processing involved in the search for the best product-unit neural network (PUNN) models [Durbin, 1990] [Martínez-Estud illo, 2006A], using evolutionary algorithms, EAs. A cluster of computers [Buyya, 1999] will be used to carry out the distribution of this processing. Many different types of neural network architectures have been used, but the most popular one has been the single-hidden-layer feedforward network. Amongst the numerous approaches that use neural networks in classification problems, we focus our attention on ev olutionary artificial neural networks (EANNs). EANNs have been a key research area in the past decade pr oviding an improved platfo rm for optimizing network performance and architecture (number of hidden nodes and number of connections) simultaneously.