22 citations · 33 across the 5 of their papers we have counts for
5 papers
On Experiments
Brendan van Rooyen
The scientific process is a means to turn the results of experiments into knowledge about the world in which we live. Much research effort has been directed toward automating this…
Learning from Binary Labels with Instance-Dependent Corruption
Aditya Krishna Menon, Brendan van Rooyen, Nagarajan Natarajan
Suppose we have a sample of instances paired with binary labels corrupted by arbitrary instance- and label-dependent noise. With sufficiently many such samples, can we optimally cl…
Learning with Symmetric Label Noise: The Importance of Being Unhinged
Brendan van Rooyen, Aditya Krishna Menon, Robert C. Williamson
Convex potential minimisation is the de facto approach to binary classification. However, Long and Servedio [2010] proved that under symmetric label noise (SLN), minimisation of an…
Learning in the Presence of Corruption
Brendan van Rooyen, Robert C. Williamson
In supervised learning one wishes to identify a pattern present in a joint distribution , of instances, label pairs, by providing a function from instances to labels that ha…
A Theory of Feature Learning
Brendan van Rooyen, Robert C. Williamson
Feature Learning aims to extract relevant information contained in data sets in an automated fashion. It is driving force behind the current deep learning trend, a set of methods t…