Benutzer: Gast  Login
Titel:

Unpaired Multi-Domain Causal Representation Learning

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Sturma, Nils; Squires, Chandler; Drton, Mathias; Uhler, Caroline
Abstract:
The goal of causal representation learning is to find a representation of data that consists of causally related latent variables. We consider a setup where one has access to data from multiple domains that potentially share a causal representation. Crucially, observations in different domains are assumed to be unpaired, that is, we only observe the marginal distribution in each domain but not their joint distribution. In this paper, we give sufficient conditions for identifiability of the joint...     »
Dewey Dezimalklassifikation:
510 Mathematik
Zeitschriftentitel:
Preprint
Jahr:
2023
Jahr / Monat:
2023-02
Quartal:
1. Quartal
Monat:
Feb
Sprache:
en
Volltext / DOI:
doi:10.48550/ARXIV.2302.00993
Verlag / Institution:
arXiv
Eingereicht (bei Zeitschrift):
02.02.2023
TUM Einrichtung:
Lehrstuhl für Mathematische Statistik, Munich Data Science Institute (MDSI); Munich Center for Machine Learning (MCML)
 BibTeX