4 papers
When does a Gaussian process have its paths in a reproducing kernel Hilbert space?
Ingo Steinwart
We investigate for which Gaussian processes there do or do not exist reproducing kernel Hilbert spaces (RKHSs) that contain almost all of their paths. In particular, we establish a…
Convergence Rates for Realizations of Gaussian Random Variables
Daniel Winkle, Ingo Steinwart, Bernard Haasdonk
This paper investigates the approximation of Gaussian random variables in Banach spaces, focusing on the high-probability bounds for the approximation of Gaussian random variables…
Conditioning of Banach Space Valued Gaussian Random Variables: An Approximation Approach Based on Martingales
Ingo Steinwart
We investigate the conditional distributions of two Banach space valued, jointly Gaussian random variables. In particular, we show that these conditional distributions are again Ga…
Convergence Analysis of a Greedy Algorithm for Conditioning Gaussian Random Variables
Daniel Winkle, Ingo Steinwart, Bernard Haasdonk
In the context of Gaussian conditioning, greedy algorithms iteratively select the most informative measurements, given an observed Gaussian random variable. However, the convergenc…