Conference item icon

Conference item

Lagrangian decomposition for neural network verification

Alternative title:
Conference paper
Abstract:

A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. Previous methods have either used off-the-shelf solvers, discarding the problem structure, or relaxed the problem even further, making the bounds unnecessarily loose. We propose a novel approach based on Lagrangian Decomposition. Our formulation admits an efficient supergradient ascent algorithm, as well as an improved proximal algorithm. Both the algorithms offer three ad...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publication website:
http://proceedings.mlr.press/v124/bunel20a.html

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Publisher:
Journal of Machine Learning Research
Host title:
Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)
Journal:
Proceedings of Machine Learning Research More from this journal
Volume:
124
Pages:
370-379
Publication date:
2020-08-27
Acceptance date:
2020-05-14
Event title:
UAI 2020: 36th Conference on Uncertainty in Artificial Intelligence
Event location:
Toronto, Canada
Event website:
http://www.auai.org/uai2020/
Event start date:
2020-08-03
Event end date:
2020-08-06
ISSN:
2640-3498
Language:
English
Keywords:
Pubs id:
1105068
Local pid:
pubs:1105068
Deposit date:
2020-05-15

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP