One approach to learning control knowledge from a problem solving trace consists of generating explanations for the local decisions made during the search process.

Probabilistic inference algorithms for belief updating, finding the most probable explanation, the maximum a posteriori hypothesis, and the maximum expected utility are reformulated within the bucket elimination framework. This emphasizes the principles common to many of the algorithms appearing

, finding the most probable explanation, and expected utility maximization. These algorithms share the same performance guarantees; all are time and space exponential in the inducedwidth of the problem's interaction graph. While elimination strategies have extensive demands on memory, a contrasting

rates. Behavioral explanations for this behavior stress bounded rationality and self-control and suggest that at least some of the low-saving households are making a mistake and would welcome aid in making decisions about their saving. In this paper, we propose such a prescriptive savings program

ABSTRACT.3 For a system of differentiable convex inequalities, a new bound is given for the absolute error in an infeasible point in terms of the absolute residual. By using this bound a condition number is defined for the system of inequalities which gives a bound for the relative error

of the error over the training set. A bound on the generalization error for the combined predictors in terms of their maximum error is proven that is sharper than bounds to date. Arcing algorithms are described that converge to the optimal strategy. Schapire et.al. [1997] offered an explanation of why Adaboost

Much attention has been paid to the theoretical explanation of the empirical success of AdaBoost. The most influential work is the margin theory, which is essentially an upper bound for the generalization error of any voting classifier in terms of the margin distribution over the training data

Datalog programs with at most k variables; this provides a new explanation for the tractability of these classes of problems. After this, we investigate constraint satisfaction on inputs that are homomorphically equivalent to structures of bounded treewidth.

bounds between successive intervals whose durations relate as simple integer ratios. The definition of the internal stability of a mental representation of rhythm depends on the contributions of these bounds. This theory i s in accordance with the responses when subjects were asked t o identify rhythmic

Margin theory provides one of the most popular explanations to the success of AdaBoost, where the central point lies in the recognition that margin is the key for characterizing the performance of AdaBoost. This theory has been very influential, e.g., it has been used to argue that AdaBoost usually