November 27, 2023 to December 1, 2023 Conference
Dual node
Europe/Paris timezone

Fishnets: Mapping Information Geometry with Robust, Scalable Neural Compression

Nov 27, 2023, 5:54 PM
3m
Dual node

Dual node

IAP (Paris) & CCA/Flatiron (New York) IAP 98bis Boulevard Arago 75014 Paris FRANCE CCA/Flatiron 5th Avenue New York (NY) USA
Flash talk Paris Contributed talks

Speakers

Benjamin Wandelt (Institut d'Astrophysique de Paris / The Flatiron Institute) Lucas Makinen (Imperial College London)

Description

Data compression to informative summaries is essential for modern data analysis. Neural regression is a popular simulation-based technique for mapping data to parameters as summaries over a prior, but is usually agnostic to how uncertainties in information geometry, or data-summary relationship, changes over parameter space. We present Fishnets, a general simulation-based, neural compression approach to calculating the Fisher information and score for arbitrary data structures as functions of parameters. These compression networks can be scaled information-optimally to arbitrary data structures, and are robust to changes in data distribution, making them ideal tools for cosmological and graph dataset analyses.

Author

Lucas Makinen (Imperial College London)

Co-authors

Benjamin Wandelt (Institut d'Astrophysique de Paris / The Flatiron Institute) Dr Justin Alsing (Stockholm University)

Presentation materials