3 papers
math.NA2025
Approximation bounds for norm constrained deep neural networks
Francesco Paolo Maiale, Anastasiia Trofimova, Arturo De Marinis
This paper studies the approximation capacity of neural networks with an arbitrary activation function and with norm constraint on the weights. Upper and lower bounds on the approx…
math.DS2025
Probabilistic Analysis of the Random Spectral Radius for a Matrix Family
Francesco Paolo Maiale, Anastasiia Trofimova, Nicola Guglielmi
We investigate joint spectral characteristics of a family of matrices , associated with products in the semigroup generated by . In the literature, extrema…
cond-mat.stat-mech2025
Scaling Properties of Current Fluctuations in Periodic TASEP
Anastasiia Trofimova, Lu Xu
We study current fluctuations in the Totally Asymmetric Simple Exclusion Process (TASEP) on a ring with sites and particles. By introducing a deformation parameter , we…