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:
-
-
(Preview, Version of record, pdf, 7.2MB, Terms of use)
-
- Publication website:
- https://proceedings.mlr.press/v202/petrov23a
Authors
- 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
- Copyright holder:
- Petrov et al
- Copyright date:
- 2023
- Rights statement:
- © 2023 by the author(s).
- Notes:
- This paper will be presented at the 40th International Conference on Machine Learning (ICML 2023), 23rd - 29th July 2023, Honolulu, Hawai'i, USA.
If you are the owner of this record, you can report an update to it here: Report update to this record