We propose a simple class of multivariate GARCH models, allowing for time-varying conditional correlations. Estimates for time-varying conditional correlations are constructed by means of a convex combination of averaged correlations (across all series) and dynamic realized (historical) correlations. Our model is very parsimonious. Estimation is computationally feasible in very large dimensions...

Abstract. The ∆2-distribution is a multivariate distribution, which plays an important role in variance reduction of Monte Carlo integral evaluation. Selecting the nodes of random cubature formulae according to ∆2 ensures an unbiased and efficient estimate of the studied integral regardless of the region it is solved over. The ∆2 distribution is also relevant in problems such as separating erro...

We examine the mechanism by which feature selection improves the accuracy of supervised learning. An empirical bias/variance analysis as feature selection progresses indicates that the most accurate feature set corresponds to the best bias-variance trade-off point for the learning algorithm. Often, this is not the point separating relevant from irrelevant features, but where increasing variance...

Some theoretical issues related to the problem of variance reduction in numerical approaches for stochastic homogenization are examined. On some simple, yet representative cases, it is demonstrated theoretically that a technique based on antithetic variables can indeed reduce the variance of the output of the computation, and decrease the overall computational cost of such a multiscale problem....

Multiple independent streams of random numbers are often required in simulation studies, for instance, to facilitate synchronization for variance-reduction purposes, and for making independent replications. A portable set of software utilities is described for uniform randomnumber generation. It provides for multiple generators (streams) running simultaneously, and each generator (stream) has i...

We propose a unified framework to speed up the existing stochastic matrix factorization (SMF) algorithms via variance reduction. Our framework is general and it subsumes several well-known SMF formulations in the literature. We perform a non-asymptotic convergence analysis of our framework and derive computational and sample complexities for our algorithm to converge to an -stationary point in ...

This paper investigates the reduction of variance associated with a simulation output performance measure, using the Sequential Sampling method while applying minimum simulation replications, for a class of JIT (Just in Time) warehousing system called crossdocking. We initially used the Sequential Sampling method to attain a desired 95% confidence interval half width of ± 0.5 for our chosen per...

A variance reduction technique in nonparametric smoothing is proposed: at each point of estimation, form a linear combination of a preliminary estimator evaluated at nearby points with the coefficients specified so that the asymptotic bias remains unchanged. The nearby points are chosen to maximize the variance reduction. We study in detail the case of univariate local linear regression. While ...

There exist many different wavelet methods for classical nonparametric regression in the statistical literature. However, techniques specifically designed for binomial intensity estimation are relatively uncommon. In this article, we propose a new technique for the estimation of the proportion of a binomial process. This method, called the Haar-NN transformation, transforms the data to be appro...