Computer Emulation with Nonstationary Gaussian Processes
نویسندگان
چکیده
منابع مشابه
Locally-Biased Bayesian Optimization using Nonstationary Gaussian Processes
Bayesian optimization is becoming a fundamental global optimization algorithm in many applications where sample efficiency is needed, ranging from automatic machine learning, robotics, reinforcement learning, experimental design, simulations, etc. The most popular and effective Bayesian optimization method relies on a stationary Gaussian process as surrogate. In this paper, we present a novel n...
متن کاملAnalyzing nonstationary spatial data using piecewise Gaussian processes
In many problems in geostatistics we find that the response variable of interest is strongly related to the underlying geology of the spatial location. In these situations there is often little correlation in the responses found in different rock strata so that the underlying covariance structure shows sharp changes at the boundaries of the rock types. Conventional stationary and nonstationary ...
متن کاملLinear interpolation of random processes and extremes of a sequence of Gaussian nonstationary processes
We consider the limit distribution of maxima for a sequence of Gaussian nonstationary processes. As an application we investigate the linear interpolation error for a.s. continuous and mean square diierentiable Gaussian processes with stationary increments. The relation between the smoothness of incremental variance function, d(t) = E(X(s + t) ? X(s)) 2 ], and the interpolation errors in mean s...
متن کاملEmulation of Computer Networks with Netkit
An emulator is a software or hardware environment that is capable of closely reproducing the functionalities of a real world system. Emulators, especially if implemented in software, are very useful for performing experiments that might compromise the operation of the target system or simply when the real system itself is not available. This is true in particular for computer networks, where co...
متن کاملNonstationary Continuous - Time Processes ∗
∗Preliminary Comments are welcome. Paper written for the Handbook of Financial Econometrics edited by Yacine Aı̈t-Sahalia and Lars Peter Hansen. We thank Darrell Duffie, Benoit Perron and Mark Watson for discussions and Seoyeon Lee for research assistance. Bandi acknowledges financial support from the IBM Corporation Faculty Research Fund at the University of Chicago. Phillips thanks fhe NSF for...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: SIAM/ASA Journal on Uncertainty Quantification
سال: 2016
ISSN: 2166-2525
DOI: 10.1137/141001512