Follow
Peter Súkeník
Peter Súkeník
PhD. student, Institute of Science and Technology, Austria
Verified email at ista.ac.at
Title
Cited by
Cited by
Year
Intriguing Properties of Input-dependent Randomized Smoothing
P Súkeník, A Kuvshinov, S Günnemann
Proceedings of the 39th International Conference on Machine Learning, PMLR …, 2021
282021
Deep neural collapse is provably optimal for the deep unconstrained features model
P Súkeník, M Mondelli, CH Lampert
Advances in Neural Information Processing Systems 36, 2024
182024
Average gradient outer product as a mechanism for deep neural collapse
D Beaglehole, P Súkeník, M Mondelli, M Belkin
arXiv preprint arXiv:2402.13728, 2024
102024
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
P Kocsis, P Súkeník, G Brasó, M Nießner, L Leal-Taixé, I Elezi
Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
92022
Generalization in multi-objective machine learning
P Súkeník, C Lampert
Neural Computing and Applications, 1-15, 2024
62024
Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
P Súkeník, CH Lampert, M Mondelli
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
4*2024
Wide neural networks trained with weight decay provably exhibit neural collapse
A Jacot, P Súkeník, Z Wang, M Mondelli
arXiv preprint arXiv:2410.04887, 2024
22024
The system can't perform the operation now. Try again later.
Articles 1–7