Peter Súkeník
Graduate School
Mondelli Group
Lampert Group
3 Publications
2023 | Conference Paper | IST-REx-ID: 14921 |
Súkeník, Peter, et al. “Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model.” 37th Annual Conference on Neural Information Processing Systems.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Preprint | IST-REx-ID: 12662 |
Súkeník, Peter, and Christoph Lampert. “Generalization in Multi-Objective Machine Learning.” ArXiv, 2208.13499, doi:10.48550/arXiv.2208.13499.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Conference Paper | IST-REx-ID: 12664 |
Súkeník, Peter, et al. “Intriguing Properties of Input-Dependent Randomized Smoothing.” Proceedings of the 39th International Conference on Machine Learning, vol. 162, ML Research Press, 2022, pp. 20697–743.
[Published Version]
View
| Files available
| arXiv
3 Publications
2023 | Conference Paper | IST-REx-ID: 14921 |
Súkeník, Peter, et al. “Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model.” 37th Annual Conference on Neural Information Processing Systems.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Preprint | IST-REx-ID: 12662 |
Súkeník, Peter, and Christoph Lampert. “Generalization in Multi-Objective Machine Learning.” ArXiv, 2208.13499, doi:10.48550/arXiv.2208.13499.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Conference Paper | IST-REx-ID: 12664 |
Súkeník, Peter, et al. “Intriguing Properties of Input-Dependent Randomized Smoothing.” Proceedings of the 39th International Conference on Machine Learning, vol. 162, ML Research Press, 2022, pp. 20697–743.
[Published Version]
View
| Files available
| arXiv