Norm convergent expansions for Gaussian processes in Banach spaces.

Greedy expansions in Banach spaces

The Gaussian Radon Transform for Banach Spaces

The classical Radon transform can be thought of as a way to obtain the density of an n-dimensional object from its (n− 1)-dimensional sections in di erent directions. A generalization of this transform to in nite-dimensional spaces has the potential to allow one to obtain a function de ned on an in nite-dimensional space from its conditional expectations. We work within a standard framework in ...

Expansions for Gaussian processes and Parseval frames

We derive a precise link between series expansions of Gaussian random vectors in a Banach space and Parseval frames in their reproducing kernel Hilbert space. The results are applied to pathwise continuous Gaussian processes and a new optimal expansion for fractional OrnsteinUhlenbeck processes is derived.

Random Feature Expansions for Deep Gaussian Processes

The composition of multiple Gaussian Processes as a Deep Gaussian Process (DGP) enables a deep probabilistic nonparametric approach to flexibly tackle complex machine learning problems with sound quantification of uncertainty. Existing inference approaches for DGP models have limited scalability and are notoriously cumbersome to construct. In this work we introduce a novel formulation of DGPs b...

Norm optimization problem for linear operators in classical Banach spaces

We prove a linear operator T acting between lp-type spaces attains its norm if, and only if, there exists a not weakly null maximizing sequence for T . For 1 < p 6= q we show that any not weakly null maximizing sequence for a norm attaining operator T : lp → lq has a norm-convergent subsequence. We also prove that for any fixed x0 in lp, the set of operators T : lp → lq that attain their norm a...