We present a generative model for representing and reasoning about the relationships among events in continuous time. We apply the model to the domain of networked and distributed computing environments where we fit the parameters of the model from timestamp observations, and then use hypothesis testing to discover dependencies between the events and changes in behavior for monitoring and diagnosis. After introducing the model, we present an EM algorithm for fitting the parameters and then present the hypothesis testing approach for both dependence discovery and change-point detection. We validate the approach for both tasks using real data from a trace of network events at Microsoft Research Cambridge. Finally, we formalize the relationship between the proposed model and the noisy-or gate for cases when time can be discretized. 1

Modern Bayesian Network learning algorithms are timeefficient, scalable and produce high-quality models; these algorithms feature prominently in decision support model development, variable selection, and causal discovery. The quality of the models, however, has often only been empirically evaluated; the available theoretical results typically guarantee asymptotic correctness (consistency) of the algorithms. This paper describes theoretical bounds on the quality of a fundamental Bayesian Network local-learning task in the finite sample using theories for controlling the False Discovery Rate. The behavior of the derived bounds is investigated across various problem and algorithm parameters. Empirical results support the theory which has immediate ramifications in the design of new algorithms for Bayesian Network learning, variable selection and causal discovery. Copyright c ○ 2008, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

This is to certify that I have examined this copy of a doctoral dissertation by

Abstract — A Bayes net has qualitative and quantitative aspects: The qualitative aspect is its graphical structure that corresponds to correlations among the variables in the Bayes net. The quantitative aspects are the net parameters. This paper develops a hybrid criterion for learning Bayes net structures that is based on both aspects. We combine model selection criteria measuring data fit with correlation information from statistical tests: Given a sample d, search for a structure G that maximizes score(G, d), over the set of structures G that satisfy the dependencies detected in d. We rely on the statistical test only to accept conditional dependencies, not conditional independencies. We show how to adapt local search algorithms to accommodate the observed dependencies. Simulation studies with GES search and the BDeu/BIC scores provide evidence that the additional dependency information leads to Bayes nets that better fit the target model in distribution and structure. I.

New challenges for feature selection

� Algorithms exist that scale up to problems with thousands of variables [7] � Decent quality of learning Experimental Evaluation

representing the official policies, either expressed or implied, of any sponsoring institution, the U.S. government

Abstract not found

Learning generative models for protein