Peter Súkeník
Graduate School
Mondelli Group
Lampert Group
4 Publications
2024 | Epub ahead of print | Journal Article | IST-REx-ID: 12662 | 
Generalization in multi-objective machine learning
P. Súkeník, C. Lampert, Neural Computing and Applications (2024).
[Published Version]
View
| DOI
| Download Published Version (ext.)
| arXiv
P. Súkeník, C. Lampert, Neural Computing and Applications (2024).
2023 | Published | Conference Paper | IST-REx-ID: 14921 |
Deep neural collapse is provably optimal for the deep unconstrained features model
P. Súkeník, M. Mondelli, C. Lampert, in:, 37th Annual Conference on Neural Information Processing Systems, 2023.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
P. Súkeník, M. Mondelli, C. Lampert, in:, 37th Annual Conference on Neural Information Processing Systems, 2023.
2022 | Published | Conference Paper | IST-REx-ID: 12664 |
Intriguing properties of input-dependent randomized smoothing
P. Súkeník, A. Kuvshinov, S. Günnemann, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022, pp. 20697–20743.
[Published Version]
View
| Files available
| arXiv
P. Súkeník, A. Kuvshinov, S. Günnemann, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022, pp. 20697–20743.
2022 | Published | Conference Paper | IST-REx-ID: 18876 |
The unreasonable effectiveness of fully-connected layers for low-data regimes
P. Kocsis, P. Súkeník, G. Brasó, M. Niessner, L. Leal-Taixé, I. Elezi, in:, 36th Conference on Neural Information Processing Systems, Curran Associates, 2022, pp. 1896–1908.
[Published Version]
View
| Files available
| arXiv
P. Kocsis, P. Súkeník, G. Brasó, M. Niessner, L. Leal-Taixé, I. Elezi, in:, 36th Conference on Neural Information Processing Systems, Curran Associates, 2022, pp. 1896–1908.
Grants
4 Publications
2024 | Epub ahead of print | Journal Article | IST-REx-ID: 12662 |
Generalization in multi-objective machine learning
P. Súkeník, C. Lampert, Neural Computing and Applications (2024).
[Published Version]
View
| DOI
| Download Published Version (ext.)
| arXiv
P. Súkeník, C. Lampert, Neural Computing and Applications (2024).
2023 | Published | Conference Paper | IST-REx-ID: 14921 |
Deep neural collapse is provably optimal for the deep unconstrained features model
P. Súkeník, M. Mondelli, C. Lampert, in:, 37th Annual Conference on Neural Information Processing Systems, 2023.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
P. Súkeník, M. Mondelli, C. Lampert, in:, 37th Annual Conference on Neural Information Processing Systems, 2023.
2022 | Published | Conference Paper | IST-REx-ID: 12664 |
Intriguing properties of input-dependent randomized smoothing
P. Súkeník, A. Kuvshinov, S. Günnemann, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022, pp. 20697–20743.
[Published Version]
View
| Files available
| arXiv
P. Súkeník, A. Kuvshinov, S. Günnemann, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022, pp. 20697–20743.
2022 | Published | Conference Paper | IST-REx-ID: 18876 |
The unreasonable effectiveness of fully-connected layers for low-data regimes
P. Kocsis, P. Súkeník, G. Brasó, M. Niessner, L. Leal-Taixé, I. Elezi, in:, 36th Conference on Neural Information Processing Systems, Curran Associates, 2022, pp. 1896–1908.
[Published Version]
View
| Files available
| arXiv
P. Kocsis, P. Súkeník, G. Brasó, M. Niessner, L. Leal-Taixé, I. Elezi, in:, 36th Conference on Neural Information Processing Systems, Curran Associates, 2022, pp. 1896–1908.