no code implementations • 20 Mar 2023 • Francesco Farina, Mike Arpaia, Harpal Khing, Jonas Vetterle
The optimal portfolio size for a venture capital (VC) fund is a topic often debated, but there is no consensus on the best strategy.
no code implementations • 6 Jul 2021 • Francesco Farina, Lawrence Phillips, Nicola J Richmond
We introduce a framework for uncertainty estimation that both describes and extends many existing methods.
no code implementations • 25 Jun 2021 • Francesco Farina, Emma Slade
We introduce a novel architecture for graph networks which is equivariant to any transformation in the coordinate embeddings that preserves the distance between neighbouring nodes.
no code implementations • 28 May 2021 • Francesco Farina, Emma Slade
Exploiting symmetries and invariance in data is a powerful, yet not fully exploited, way to achieve better generalisation with more efficiency.
no code implementations • 25 Mar 2021 • Emma Slade, Francesco Farina
In this draft paper, we introduce a novel architecture for graph networks which is equivariant to the Euclidean group in $n$-dimensions.
no code implementations • 3 Sep 2020 • Guido Carnevale, Francesco Farina, Ivano Notarnicola, Giuseppe Notarstefano
This paper deals with a network of computing agents aiming to solve an online optimization problem in a distributed fashion, i. e., by means of local computation and communication, without any central coordinator.
no code implementations • 10 Aug 2020 • Ivano Notarnicola, Andrea Simonetto, Francesco Farina, Giuseppe Notarstefano
We present a distributed optimization algorithm for solving online personalized optimization problems over a network of computing and communicating nodes, each of which linked to a specific user.
no code implementations • 5 Dec 2019 • Francesco Farina
In this paper, we introduce the concept of collective learning (CL) which exploits the notion of collective intelligence in the field of distributed semi-supervised learning.
no code implementations • 13 Nov 2019 • Francesco Farina, Stefano Melacci, Andrea Garulli, Antonio Giannitrapani
In this paper, the extension of the framework of Learning from Constraints (LfC) to a distributed setting where multiple parties, connected over the network, contribute to the learning process is studied.
no code implementations • 31 May 2019 • Andrea Testa, Francesco Farina, Giuseppe Notarstefano
In this \emph{distributed} set-up, in order to preserve their own privacy, agents communicate with neighbors but do not share their local cost functions.
1 code implementation • 17 Mar 2018 • Francesco Farina, Andrea Garulli, Antonio Giannitrapani, Giuseppe Notarstefano
We show that this distributed algorithm is equivalent to a block coordinate descent algorithm for the minimization of the Augmented Lagrangian followed by an update of the whole multiplier vector.
Optimization and Control