We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out e...
We introduce a general-purpose learning machine that we call the Guaranteed Error Machine, or GEM, and two learning algorithms, a real GEM algorithm and an ideal GEM algorithm. Th...
This paper presents distributed bounded-error parameter and state estimation algorithms suited to measurement processing by a network of sensors. Contrary to centralized estimation...
This paper introduces a new PAC transductive error bound for classification. The method uses information from the training examples and inputs of working examples to develop a set...
Dimensionally unbounded problems are frequently encountered in practice, such as in simulations of stochastic processes, in particle and light transport problems and in the problem...