Peter Súkeník
Graduate School
Mondelli Group
Lampert Group
6 Publications
2024 | Epub ahead of print | Journal Article | IST-REx-ID: 12662 | 
Súkeník, P., & Lampert, C. (2024). Generalization in multi-objective machine learning. Neural Computing and Applications. Springer Nature. https://doi.org/10.1007/s00521-024-10616-1
[Published Version]
View
| DOI
| Download Published Version (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18890 |
Beaglehole, D., Súkeník, P., Mondelli, M., & Belkin, M. (2024). Average gradient outer product as a mechanism for deep neural collapse. In 38th Annual Conference on Neural Information Processing Systems (Vol. 37). Vancouver, Canada: Neural Information Processing Systems Foundation.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18891 |
Súkeník, P., Lampert, C., & Mondelli, M. (2024). Neural collapse versus low-rank bias: Is deep neural collapse really optimal? In 38th Annual Conference on Neural Information Processing Systems (Vol. 37). Vancouver, Canada: Neural Information Processing Systems Foundation.
[Published Version]
View
| Files available
2023 | Published | Conference Paper | IST-REx-ID: 14921 |
Súkeník, P., Mondelli, M., & Lampert, C. (2023). 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.
[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 |
Súkeník, P., & Lampert, C. (2024). Generalization in multi-objective machine learning. Neural Computing and Applications. Springer Nature. https://doi.org/10.1007/s00521-024-10616-1
[Published Version]
View
| DOI
| Download Published Version (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18890 |
Beaglehole, D., Súkeník, P., Mondelli, M., & Belkin, M. (2024). Average gradient outer product as a mechanism for deep neural collapse. In 38th Annual Conference on Neural Information Processing Systems (Vol. 37). Vancouver, Canada: Neural Information Processing Systems Foundation.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2024 | Published | Conference Paper | IST-REx-ID: 18891 |
Súkeník, P., Lampert, C., & Mondelli, M. (2024). Neural collapse versus low-rank bias: Is deep neural collapse really optimal? In 38th Annual Conference on Neural Information Processing Systems (Vol. 37). Vancouver, Canada: Neural Information Processing Systems Foundation.
[Published Version]
View
| Files available
2023 | Published | Conference Paper | IST-REx-ID: 14921 |
Súkeník, P., Mondelli, M., & Lampert, C. (2023). 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.
[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