Gaussian approximation of general non-parametric posterior distributions
نویسندگان
چکیده
منابع مشابه
Posterior consistency for Gaussian process approximations of Bayesian posterior distributions
We study the use of Gaussian process emulators to approximate the parameter-to-observation map or the negative log-likelihood in Bayesian inverse problems. We prove error bounds on the Hellinger distance between the true posterior distribution and various approximations based on the Gaussian process emulator. Our analysis includes approximations based on the mean of the predictive process, as w...
متن کاملSparse-posterior Gaussian Processes for general likelihoods
Gaussian processes (GPs) provide a probabilistic nonparametric representation of functions in regression, classification, and other problems. Unfortunately, exact learning with GPs is intractable for large datasets. A variety of approximate GP methods have been proposed that essentially map the large dataset into a small set of basis points. Among them, two state-of-the-art methods are sparse p...
متن کاملSparse-posterior Gaussian Processes for general likelihoods
Gaussian processes (GPs) provide a probabilistic nonparametric representation of functions in regression, classification, and other problems. Unfortunately, exact learning with GPs is intractable for large datasets. A variety of approximate GP methods have been proposed that essentially map the large dataset into a small set of basis points. Among them, two state-of-the-art methods are sparse p...
متن کاملSample Variance of non-Gaussian Sky Distributions
Non-Gaussian distributions of cosmic microwave background (CMB) anisotropies have been proposed to reconcile the discrepancies between different experiments at half-degree scales (Coulson et al. 1994). Each experiment probes a different part of the sky, furthermore, sky coverage is very small, hence the sample variance of each experiment can be large, especially when the sky signal is non-Gauss...
متن کاملParametric Sensitivity Analysis Using Large-Sample Approximate Bayesian Posterior Distributions
W a decision analyst desires a sensitivity analysis on model parameters that are estimated from data, a natural approach is to vary each parameter within one or two standard errors of its estimate. This approach can be problematic if parameter estimates are correlated or if model structure does not permit obvious standard error estimates. Both of these difficulties can occur when the analysis o...
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: Information and Inference: A Journal of the IMA
سال: 2017
ISSN: 2049-8764,2049-8772
DOI: 10.1093/imaiai/iax017