no code implementations • 29 Aug 2022 • Reilly Raab, Luca de Alfaro, Yang Liu
We prove that Fisher-Rao natural gradient descent (FR-NGD) optimally approximates the continuous time replicator equation (an essential model of evolutionary dynamics), and term this correspondence "conjugate natural selection".
no code implementations • 17 Aug 2021 • Eliana Pastor, Luca de Alfaro, Elena Baralis
Furthermore, we quantify the contribution of all attributes in the data subgroup to the divergent behavior by means of Shapley values, thus allowing the identification of the most impacting attributes.
1 code implementation • 11 Mar 2019 • Rakshit Agrawal, Luca de Alfaro
Graph edges, along with their labels, can represent information of fundamental importance, such as links between web pages, friendship between users, the rating given by users to other users or items, and much more.
1 code implementation • 1 Feb 2019 • Rakshit Agrawal, Luca de Alfaro, David Helmbold
The provable accuracy of MWD networks is superior even to the observed accuracy of ReLU networks trained with the help of adversarial examples.
no code implementations • ICLR 2019 • Luca de Alfaro
On permutation-invariant MNIST, in absence of adversarial attacks, networks using RBFI units match the performance of networks using sigmoid units, and are slightly below the accuracy of networks with ReLU units.
1 code implementation • 25 Apr 2017 • Eugenio Tacchini, Gabriele Ballarin, Marco L. Della Vedova, Stefano Moret, Luca de Alfaro
As a contribution towards this objective, we show that Facebook posts can be classified with high accuracy as hoaxes or non-hoaxes on the basis of the users who "liked" them.
no code implementations • 21 Nov 2016 • Rakshit Agrawal, Luca de Alfaro, Vassilis Polychronopoulos
Many prediction problems can be phrased as inferences over local neighborhoods of graphs.