Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG.

Jonas Seng; Matej Zecevic; Devendra Singh Dhami; Kristian Kersting

Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG.

Jonas Seng, Matej Zecevic, Devendra Singh Dhami, Kristian Kersting

Uncertainty in Artificial Intelligence

Research output: Contribution to conference › Paper › Academic

Original language	Undefined
Publication status	Published - 2024

Bibliographical note

DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

Access to Document

https://dblp.org/rec/conf/iclr/SengZDK24

Cite this

@conference{e0de4cd21f014553b212554974dd41af,

title = "Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG.",

author = "Jonas Seng and Matej Zecevic and Dhami, {Devendra Singh} and Kristian Kersting",

note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2024",

language = "Niet gedefinieerd",

}

TY - CONF

T1 - Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG.

AU - Seng, Jonas

AU - Zecevic, Matej

AU - Dhami, Devendra Singh

AU - Kersting, Kristian

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2024

Y1 - 2024

M3 - Paper

ER -