3 citations · 3 across the 4 of their papers we have counts for
4 papers
A General Constructive Upper Bound on Shallow Neural Nets Complexity
Frantisek Hakl, Vit Fojtik
We provide an upper bound on the number of neurons required in a shallow neural network to approximate a continuous function on a compact set with a given accuracy. This method, in…
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…
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…
On exact computation of Tukey depth central regions
Vít Fojtík, Petra Laketa, Pavlo Mozharovskyi +1
The Tukey (or halfspace) depth extends nonparametric methods toward multivariate data. The multivariate analogues of the quantiles are the central regions of the Tukey depth, defin…