4 papers
Approximation properties of neural ODEs
Arturo De Marinis, Davide Murari, Elena Celledoni +3
We study the approximation properties of neural ordinary differential equations (neural ODEs) in the space of continuous functions. Since a neural ODE requires input and output dim…
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…
Improving the robustness of neural ODEs with minimal weight perturbation
Arturo De Marinis, Nicola Guglielmi, Stefano Sicilia +1
We propose a method to enhance the stability of a neural ordinary differential equation (neural ODE) by reducing the maximum error growth subsequent to a perturbation of the initia…
Contractivity of neural ODEs: an eigenvalue optimization problem
Nicola Guglielmi, Arturo De Marinis, Anton Savostianov +1
We propose a novel methodology to solve a key eigenvalue optimization problem which arises in the contractivity analysis of neural ODEs. When looking at contractivity properties of…