Benutzer: Gast  Login
Titel:

Unpaired Multi-Domain Causal Representation Learning

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Sturma, Nils; Squires, Chandler; Drton, Mathias; Uhler, Caroline
Seitenangaben Beitrag:
34465--34492
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
Kongress- / Buchtitel:
Advances in Neural Information Processing Systems 36
Kongress / Zusatzinformationen:
37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)
Datum der Konferenz:
December 10 - 16, 2023
Jahr:
2023
Quartal:
4. Quartal
WWW:
NeurIPS 2023
Semester:
WS 23-24
TUM Einrichtung:
Lehrstuhl für Mathematische Statistik
Format:
Text
 BibTeX