Fetching the paper…

Reading the bibliography…

2016

Deep Multi-fidelity Gaussian Processes

Raissi, Maziar, Karniadakis, George

Original
PDF
Post on X

Understand

We develop a novel multi-fidelity framework that goes far beyond the classical AR(1) Co-kriging scheme of Kennedy and O'Hagan (2000).

Our method can handle general discontinuous cross-correlations among systems with different levels of fidelity.
A combination of multi-fidelity Gaussian Processes (AR(1) Co-kriging) and deep neural networks enables us to construct a method that is immune to discontinuities.
We demonstrate the effectiveness of the new technology using standard benchmark problems designed to resemble the outputs of complicated high- and low-fidelity codes.

Deep Multi-fidelity Gaussian Processes · Around

Built on

Predicting the output from a complex computer code when fast approximations are available
Kennedy, Marc C and O’Hagan, Anthony · 2000
Earlier work this paper cites.
Gaussian processes for machine learning
Original
Christopher KI Williams and Carl Edward Rasmussen · 2006
Earlier work this paper cites.

Similar

Multi-fidelity optimization via surrogate modelling
Alexander IJ Forrester, András Sóbester, and Andy J Keane · 2007
Cited alongside, same era.
Manifold gaussian processes for regression
Original
Roberto Calandra, Jan Peters, Carl Edward Rasmussen, and Marc Peter Deisenroth · 2014
Cited alongside, same era.

Then

Deep Gaussian processes and variational propagation of uncertainty
Andreas Damianou · 2015
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…