10 citations · 41 across the 9 of their papers we have counts for
7 papers · 1 filter
The Geometry and Calculus of Losses
Robert C. Williamson, Zac Cranko
Statistical decision problems lie at the heart of statistical machine learning. The simplest problems are binary and multiclass classification and class probability estimation. Cen…
Information Processing Equalities and the Information-Risk Bridge
Robert C. Williamson, Zac Cranko
We introduce two new classes of measures of information for statistical experiments which generalise and subsume -divergences, integral probability metrics, -dista…
Generalised Lipschitz Regularisation Equals Distributional Robustness
Zac Cranko, Zhan Shi, Xinhua Zhang +2
The problem of adversarial examples has highlighted the need for a theory of regularisation that is general enough to apply to exotic function classes, such as universal approximat…
Proper-Composite Loss Functions in Arbitrary Dimensions
Zac Cranko, Robert C. Williamson, Richard Nock
The study of a machine learning problem is in many ways is difficult to separate from the study of the loss function being used. One avenue of inquiry has been to look at these los…
Monge blunts Bayes: Hardness Results for Adversarial Training
Zac Cranko, Aditya Krishna Menon, Richard Nock +3
The last few years have seen a staggering number of empirical studies of the robustness of neural networks in a model of adversarial perturbations of their inputs. Most rely on an…
Boosted Density Estimation Remastered
Zac Cranko, Richard Nock
There has recently been a steady increase in the number iterative approaches to density estimation. However, an accompanying burst of formal convergence guarantees has not followed…
f-GANs in an Information Geometric Nutshell
Richard Nock, Zac Cranko, Aditya Krishna Menon +2
Nowozin \textit{et al} showed last year how to extend the GAN \textit{principle} to all -divergences. The approach is elegant but falls short of a full description of the superv…