no code implementations • 17 Jan 2024 • Massimiliano Datres, Gian Paolo Leonardi, Alessio Figalli, David Sutter
We introduce a novel capacity measure 2sED for statistical models based on the effective dimension.
no code implementations • CVPR 2022 • Matteo Spallanzani, Gian Paolo Leonardi, Luca Benini
When testing ANA on the CIFAR-10 image classification benchmark, we find that the major impact on task accuracy is not due to the qualitative shape of the regularisations but to the proper synchronisation of the different STE variants used in a network, in accordance with the theoretical results.
no code implementations • 3 Nov 2020 • Gian Paolo Leonardi, Matteo Spallanzani
Research in computational deep learning has directed considerable efforts towards hardware-oriented optimisations for deep neural networks, via the simplification of the activation functions, or the quantization of both activations and weights.
no code implementations • 19 Dec 2019 • Gian Paolo Leonardi, Giorgio Saracco
We provide a geometric characterization of the minimal and maximal minimizer of the prescribed curvature functional $P(E)-\kappa |E|$ among subsets of a Jordan domain $\Omega$ with no necks of radius $\kappa^{-1}$, for values of $\kappa$ greater than or equal to the Cheeger constant of $\Omega$.
Analysis of PDEs 49Q10, 35J93, 49Q20
1 code implementation • 24 May 2019 • Matteo Spallanzani, Lukas Cavigelli, Gian Paolo Leonardi, Marko Bertogna, Luca Benini
We present a theoretical and experimental investigation of the quantization problem for artificial neural networks.