Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
Maria Matveev, Vit Fojtik, Hung-Hsu Chou +2
The remarkable generalization properties of overparameterized networks are often attributed to implicit biases, such as norm minimization at small learning rates and low sharpness…
cs.LG2024
Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization
Holger Boche, Vit Fojtik, Adalbert Fono +1
The unwavering success of deep learning in the past decade led to the increasing prevalence of deep learning methods in various application fields. However, the downsides of deep l…