We formulate a robust optimal stopping-time problem for a state-space system and give the connection between various notions of lower value function for the associated games (and storage function for the associated dissipative system) with solutions of the appropriate variational inequality (VI) (the analogue of the HamiltonJacobi-Bellman-Isaacs equation for this setting). We show that the stop...

This research is a conceptual replication of a study by Browne, Pitts, and Wetherbe (2007) that explores information stopping rules in an online search context. Information stopping rules consider the cognitive reasons decision makers determine when enough information is collected to make a decision. Previous research outlines five stopping rules decision makers use and applies them in differen...

The optimal stopping rules with multiple selections of m 1 objects with the objective of maximizing the probability of obtaining the best object are studied for two problems with an unknown number of objects:the problem with a random number of objects, and the problem where the objects arrive according to a homogeneous Poisson process with unknown intensity . These two problems are variation of...

In this paper, we study a family of gradient descent algorithms to approximate the regression function from reproducing kernel Hilbert spaces. Here early stopping plays a role of regularization, where given a finite sample and some regularity condition on the regression function, a stopping rule is given and some probabilistic upper bounds are obtained for the distance between the function iter...

Abstract We suppose that a Lévy process is observed at discrete time points. Starting from an asymptotically minimax family of estimators for the continuous part Khinchine characteristics, i.e., covariance, we derive data-driven parameter choice frequency estimating covariance. investigate Lepskiĭ-type stopping rule adaptive procedure. Consequently, use balancing principle best possible paramet...

We show that Nesterov acceleration is an optimal-order iterative regularization method for linear ill-posed problems provided a parameter chosen accordingly to the smoothness of solution. This result proven both priori stopping rule and discrepancy principle. The essential tool obtain this representation residual polynomials via Gegenbauer polynomials.

Fuzzy Decision Tree (FDT) classifiers combine decision trees with approximate reasoning offered by fuzzy representation to deal with language and measurement uncertainties. When a FDT induction algorithm utilizes stopping criteria for early stopping of the tree's growth, threshold values of stopping criteria will control the number of nodes. Finding a proper threshold value for a stopping crite...

The use of the expectation-maximization algorithm to obtain pseudo-maximum likelihood estimates (i.e. the EM-ML algorithm) of radiopharmaceutical distributions based on data collected from emission computed tomography (ECT) systems is now a well developed area, as witnessed by a number of recent articles on that topic, including the detailed study of the relative performance of EM-ML and FBP re...

We study the convergence of regularized Newton methods applied to nonlinear operator equations in Hilbert spaces if the data are perturbed by random noise. It is shown that the expected square error is bounded by a constant times the minimax rates of the corresponding linearized problem if the stopping index is chosen using a-priori knowledge of the smoothness of the solution. For unknown smoot...