Search Results for author:
Found 7 papers, 3 papers with code
Conjugate Natural Selection
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".
Identifying Biased Subgroups in Ranking and Classification
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.
Learning Edge Properties in Graphs from Path Aggregations
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.
A New Family of Neural Networks Provably Resistant to Adversarial Attacks
The provable accuracy of MWD networks is superior even to the observed accuracy of ReLU networks trained with the help of adversarial examples.
Neural Networks with Structural Resistance to Adversarial Attacks
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.
Some Like it Hoax: Automated Fake News Detection in Social Networks
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.
Learning From Graph Neighborhoods Using LSTMs
Many prediction problems can be phrased as inferences over local neighborhoods of graphs.
