Accurate Emulators for Large - Scale Computer Experiments
نویسندگان
چکیده
Large-scale computer experiments are becoming increasingly important in science. A multi-step procedure is introduced to statisticians for modeling such experiments, which builds an accurate interpolator in multiple steps. In practice, the procedure shows substantial improvements in overall accuracy, but its theoretical properties are not well established. We introduce the terms nominal and numeric error and decompose the overall error of an interpolator into nominal and numeric portions. Bounds on the numeric and nominal error are developed to show theoretically that substantial gains in overall accuracy can be attained with the multi-step approach.
منابع مشابه
Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions
Gaussian process emulator with separable covariance function has been utilized extensively in modelling large computer model outputs. The assumption of separability imposes constraints on the emulator and may negatively affect its performance in some applications where separability may not hold. We propose a multi-output Gaussian process emulator with a nonseparable autocovariance function to a...
متن کاملA Network Emulator on the NetFPGA Platform
Network emulators play an important role when researchers want to evaluate the performance of newly designed protocols or network mechanisms instead of deploying them in real networks, because network emulators can provide appropriate network situations, (for example, delay, bottleneck bandwidth and packet loss) needed for experiments through easy control ‘knobs’. In this paper, we have impleme...
متن کاملExploiting Variance Reduction Potential in Local Gaussian Process Search
Gaussian process models are commonly used as emulators for computer experiments. However, developing a Gaussian process emulator can be computationally prohibitive when the number of experimental samples is even moderately large. Local Gaussian process approximation (Gramacy and Apley, 2015) was proposed as an accurate and computationally feasible emulation alternative. However, constructing lo...
متن کاملPotentially Predictive Variance Reducing Subsample Locations in Local Gaussian Process Regression
Gaussian process models are commonly used as emulators for computer experiments. However, developing a Gaussian process emulator can be computationally prohibitive when the number of experimental samples is even moderately large. Local Gaussian process approximation (Gramacy and Apley, 2015) has been proposed as an accurate and computationally feasible emulation technique. Constructing sub-desi...
متن کاملScalable Emulator for Software Defined Networks
Since its inception, Software Defined Network (SDN) has made itself a very appealing architecture for both Data Center and Wide Area networks by offering more automated control through programmability and simplified network operations and management with its centralized control plane. However, extensive rollout of SDN in the production environment requires thorough validation. Thus, there is a ...
متن کامل