Conference item icon

Conference item

Certifying ensembles: a general certification theory with s-lipschitzness

Abstract:
Improving and guaranteeing the robustness of deep learning models has been a topic of intense research. Ensembling, which combines several classifiers to provide a better model, has shown to be beneficial for generalisation, uncertainty estimation, calibration, and mitigating the effects of concept drift. However, the impact of ensembling on certified robustness is less well understood. In this work, we generalise Lipschitz continuity by introducing S-Lipschitz classifiers, which we use to analyse the theoretical robustness of ensembles. Our results are precise conditions when ensembles of robust classifiers are more robust than any constituent classifier, as well as conditions when they are less robust.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publication website:
https://proceedings.mlr.press/v202/petrov23a

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author


Publisher:
Journal of Machine Learning Research
Volume:
202
Pages:
27709-27736
Series:
Proceedings of Machine Learning Research
Publication date:
2023-08-31
Acceptance date:
2023-04-24
Event title:
40th International Conference on Machine Learning (ICML 2023)
Event location:
Honolulu, Hawai'i, USA
Event website:
https://icml.cc/
Event start date:
2023-07-23
Event end date:
2023-07-29


Language:
English
Keywords:
Pubs id:
1341180
Local pid:
pubs:1341180
Deposit date:
2023-05-15

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