22 citations · 44 across the 7 of their papers we have counts for
4 papers · 1 filter
Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
Konstantin Nikolaou, Jonas Scheunemann, Sven Krippendorf +2
Neural scaling laws describe predictable power-law relationships between model size, dataset size, compute, and performance. While these laws guide the development of modern founda…
Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens
Konstantin Nikolaou, Sven Krippendorf, Samuel Tovey +1
Scaling laws offer valuable insights into the relationship between neural network performance and computational cost, yet their underlying mechanisms remain poorly understood. In t…
Towards a Phenomenological Understanding of Neural Networks: Data
Samuel Tovey, Sven Krippendorf, Konstantin Nikolaou +1
A theory of neural networks (NNs) built upon collective variables would provide scientists with the tools to better understand the learning process at every stage. In this work, we…
Improving Simulations with Symmetry Control Neural Networks
Marc Syvaeri, Sven Krippendorf
The dynamics of physical systems is often constrained to lower dimensional sub-spaces due to the presence of conserved quantities. Here we propose a method to learn and exploit suc…