Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks
Ibrahim Talha Ersoy, Karoline Wiesner
Deep neural networks (DNNs) exhibit first order phase transitions under variations of the L2 regularization strength, with each transition marking the onset of a new learnable feat…
cs.LG2025
Phase transitions reveal hierarchical structure in deep neural networks
Ibrahim Talha Ersoy, Andrés Fernando Cardozo Licha, Karoline Wiesner
Training Deep Neural Networks relies on the model converging on a high-dimensional, non-convex loss landscape toward a good minimum. Yet, much of the phenomenology of training rema…
cs.LG2025
Phase Transitions between Accuracy Regimes in L2 regularized Deep Neural Networks
Ibrahim Talha Ersoy, Karoline Wiesner
Increasing the L2 regularization of Deep Neural Networks (DNNs) causes a first-order phase transition into the under-parametrized phase -- the so-called onset-of learning. We expla…