ML Anthology

Súkeník, Peter

7 publications

NeurIPS 2025 Neural Collapse Is Globally Optimal in Deep Regularized ResNets and Transformers Peter Súkeník, Christoph H. Lampert, Marco Mondelli
ICLR 2025 Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse Arthur Jacot, Peter Súkeník, Zihan Wang, Marco Mondelli
NeurIPS 2024 Average Gradient Outer Product as a Mechanism for Deep Neural Collapse Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin
ICMLW 2024 Neural Collapse Versus Low-Rank Bias: Is Deep Neural Collapse Really Optimal? Peter Súkeník, Marco Mondelli, Christoph H. Lampert
NeurIPS 2024 Neural Collapse vs. Low-Rank Bias: Is Deep Neural Collapse Really Optimal? Peter Súkeník, Christoph Lampert, Marco Mondelli
NeurIPS 2023 Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model Peter Súkeník, Marco Mondelli, Christoph H. Lampert
NeurIPS 2022 The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes Peter Kocsis, Peter Súkeník, Guillem Braso, Matthias Niessner, Laura Leal-Taixé, Ismail Elezi