English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Toward Bayesian data compression

Harth-Kitzerow, J., Leike, R. H., Arras, P., & Enßlin, T. A. (2021). Toward Bayesian data compression. Annalen der Physik, 533(3): 2000508. doi:10.1002/andp.202000508.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
Toward Bayesian Data Compression.pdf (Any fulltext), 5MB
 
File Permalink:
-
Name:
Toward Bayesian Data Compression.pdf
Description:
-
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Harth-Kitzerow, Johannes1, Author              
Leike, Reimar H.2, Author              
Arras, Philipp3, Author              
Enßlin, Torsten A.3, Author              
Affiliations:
1MPI for Astrophysics, Max Planck Society, ou_159875              
2Physical Cosmology, MPI for Astrophysics, Max Planck Society, ou_2205644              
3Computational Structure Formation, MPI for Astrophysics, Max Planck Society, ou_2205642              

Content

show
hide
Free keywords: -
 Abstract: In order to handle large datasets omnipresent in modern science, efficient compression algorithms are necessary. Here, a Bayesian data compression (BDC) algorithm that adapts to the specific measurement situation is derived in the context of signal reconstruction. BDC compresses a dataset under conservation of its posterior structure with minimal information loss given the prior knowledge on the signal, the quantity of interest. Its basic form is valid for Gaussian priors and likelihoods. For constant noise standard deviation, basic BDC becomes equivalent to a Bayesian analog of principal component analysis. Using metric Gaussian variational inference, BDC generalizes to non‐linear settings. In its current form, BDC requires the storage of effective instrument response functions for the compressed data and corresponding noise encoding the posterior covariance structure. Their memory demand counteract the compression gain. In order to improve this, sparsity of the compressed responses can be obtained by separating the data into patches and compressing them separately. The applicability of BDC is demonstrated by applying it to synthetic data and radio astronomical data. Still the algorithm needs further improvement as the computation time of the compression and subsequent inference exceeds the time of the inference with the original data.

Details

show
hide
Language(s):
 Dates: 2021-02-08
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1002/andp.202000508
Other: LOCALID: 3292607
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Annalen der Physik
  Other : Ann. Phys.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Weinheim : Wiley-VCH
Pages: - Volume / Issue: 533 (3) Sequence Number: 2000508 Start / End Page: - Identifier: Other: 0003-3804
CoNE: https://pure.mpg.de/cone/journals/resource/954925379961