Peter Súkeník
Graduate School
Mondelli Group
Lampert Group
6 Publications
2024 | Epub ahead of print | Journal Article | IST-REx-ID: 12662 | 
P. Súkeník and C. Lampert, “Generalization in multi-objective machine learning,” Neural Computing and Applications. Springer Nature, 2024.
[Published Version]
View
| DOI
| Download Published Version (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18890 |
D. Beaglehole, P. Súkeník, M. Mondelli, and M. Belkin, “Average gradient outer product as a mechanism for deep neural collapse,” in 38th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18891 |
P. Súkeník, C. Lampert, and M. Mondelli, “Neural collapse versus low-rank bias: Is deep neural collapse really optimal?,” in 38th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37.
[Published Version]
View
| Files available
2023 | Published | Conference Paper | IST-REx-ID: 14921 |
P. Súkeník, M. Mondelli, and C. Lampert, “Deep neural collapse is provably optimal for the deep unconstrained features model,” in 37th Annual Conference on Neural Information Processing Systems, New Orleans, LA, United States, 2023.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Published | Conference Paper | IST-REx-ID: 18876 |
Kocsis, Peter, The unreasonable effectiveness of fully-connected layers for low-data regimes. 36th Conference on Neural Information Processing Systems 35. 2022
[Published Version]
View
| Files available
| arXiv
2022 | Published | Conference Paper | IST-REx-ID: 12664 |
Súkeník, Peter, Intriguing properties of input-dependent randomized smoothing. Proceedings of the 39th International Conference on Machine Learning 162. 2022
[Published Version]
View
| Files available
| arXiv
Grants
6 Publications
2024 | Epub ahead of print | Journal Article | IST-REx-ID: 12662 |
P. Súkeník and C. Lampert, “Generalization in multi-objective machine learning,” Neural Computing and Applications. Springer Nature, 2024.
[Published Version]
View
| DOI
| Download Published Version (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18890 |
D. Beaglehole, P. Súkeník, M. Mondelli, and M. Belkin, “Average gradient outer product as a mechanism for deep neural collapse,” in 38th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18891 |
P. Súkeník, C. Lampert, and M. Mondelli, “Neural collapse versus low-rank bias: Is deep neural collapse really optimal?,” in 38th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37.
[Published Version]
View
| Files available
2023 | Published | Conference Paper | IST-REx-ID: 14921 |
P. Súkeník, M. Mondelli, and C. Lampert, “Deep neural collapse is provably optimal for the deep unconstrained features model,” in 37th Annual Conference on Neural Information Processing Systems, New Orleans, LA, United States, 2023.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Published | Conference Paper | IST-REx-ID: 18876 |
Kocsis, Peter, The unreasonable effectiveness of fully-connected layers for low-data regimes. 36th Conference on Neural Information Processing Systems 35. 2022
[Published Version]
View
| Files available
| arXiv
2022 | Published | Conference Paper | IST-REx-ID: 12664 |
Súkeník, Peter, Intriguing properties of input-dependent randomized smoothing. Proceedings of the 39th International Conference on Machine Learning 162. 2022
[Published Version]
View
| Files available
| arXiv