Peter Súkeník

According to our database, Peter Súkeník authored at least 7 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse.

Arthur Jacot, Peter Súkeník, Zihan Wang, Marco Mondelli

CoRR, 2024

Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?

Peter Súkeník, Marco Mondelli, Christoph Lampert

CoRR, 2024

Average gradient outer product as a mechanism for deep neural collapse.

Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin

CoRR, 2024

2023

Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model.

Peter Súkeník, Marco Mondelli, Christoph H. Lampert

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Generalization In Multi-Objective Machine Learning.

Peter Súkeník, Christoph H. Lampert

CoRR, 2022

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes.

Peter Kocsis, Peter Súkeník, Guillem Brasó, Matthias Nießner, Laura Leal-Taixé, Ismail Elezi

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Intriguing Properties of Input-Dependent Randomized Smoothing.

Peter Súkeník, Aleksei Kuvshinov, Stephan Günnemann

Proceedings of the International Conference on Machine Learning, 2022