Print  Close

Emulating Functional Output of Dark Matter Power Spectra Using Deep Gaussian Processes

Abstract Number:

2947 

Submission Type:

Contributed Abstract 

Contributed Abstract Type:

Speed 

Participants:

Stephen Walsh (1), Annie Booth (2), David Higdon (3), Marco Ferreira (3)

Institutions:

(1) Elms College, N/A, (2) NC State University, N/A, (3) Virginia Tech, N/A

Co-Author(s):

Annie Booth  
NC State University
David Higdon  
Virginia Tech
Marco Ferreira  
Virginia Tech

First Author:

Stephen Walsh  
Elms College

Presenting Author:

Stephen Walsh  
Elms College

Abstract Text:

We construct a framework combining Gaussian processes and hierarchical modeling to estimate and emulate dark matter power spectra from multiple, dependent computer model simulations. We model the spectra as deep Gaussian processes, and consider multiple candidate models for the covariance structure of the simulations' deviations from the true spectra. Applying the best candidate model to the expensive simulations, we estimate the underlying power spectrum for a given cosmology. With these estimates calculated across multiple cosmologies, we build an emulator using functional principal components (and Gaussian processes on the weights) for unobserved cosmologies. We obtain promising results comparing against an existing method.

Keywords:

Gaussian processes|Bayesian modeling|Hierarchical modeling|Deep Gaussian processes|Cosmology|

Sponsors:

Section on Bayesian Statistical Science

Tracks:

Applications in Applied Sciences

Can this be considered for alternate subtype?

Yes

Are you interested in volunteering to serve as a session chair?

No

I have read and understand that JSM participants must abide by the Participant Guidelines.

Yes

I understand that JSM participants must register and pay the appropriate registration fee by June 1, 2024. The registration fee is non-refundable.

I understand