Peter Súkeník

1. Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model
   2023/05/22 by Peter Súkeník, Súkeník, Peter, Marco Mondelli +3 · 7 citations
   Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM
2. Intriguing Properties of Input-dependent Randomized Smoothing
   2021/10/11 by Peter Súkeník, Aleksei Kuvshinov, Súkeník, Peter +3 · 3 citations
   Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
3. Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
   2025/05/21 by Peter Súkeník, Súkeník, Peter, Christoph H. Lampert +3 · 3 citations
   Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications