
PACBayesian Bound for the Conditional Value at Risk
Conditional Value at Risk (CVaR) is a family of "coherent risk measures"...
read it

ProperComposite Loss Functions in Arbitrary Dimensions
The study of a machine learning problem is in many ways is difficult to ...
read it

Adversarial Networks and Autoencoders: The PrimalDual Relationship and Generalization Bounds
Since the introduction of Generative Adversarial Networks (GANs) and Var...
read it

Fairness risk measures
Ensuring that classifiers are nondiscriminatory or fair with respect to...
read it

ExpConcavity of Proper Composite Losses
The goal of online prediction with expert advice is to find a decision s...
read it

Minimax Lower Bounds for Cost Sensitive Classification
The costsensitive classification problem plays a crucial role in missio...
read it

Constant Regret, Generalized Mixability, and Mirror Descent
We consider the setting of prediction with expert advice; a learner make...
read it

Generalized Mixability Constant Regret, Generalized Mixability, and Mirror Descent
We consider the setting of prediction with expert advice; a learner make...
read it

fGANs in an Information Geometric Nutshell
Nowozin et al showed last year how to extend the GAN principle to all f...
read it

Fast rates in statistical and online learning
The speed with which a learning algorithm converges as it is presented w...
read it

An Average Classification Algorithm
Many classification algorithms produce a classifier that is a weighted a...
read it

Learning in the Presence of Corruption
In supervised learning one wishes to identify a pattern present in a joi...
read it

A Theory of Feature Learning
Feature Learning aims to extract relevant information contained in data ...
read it

Generalised Mixability, Constant Regret, and Bayesian Updating
Mixability of a loss is known to characterise when constant regret bound...
read it

Le Cam meets LeCun: Deficiency and Generic Feature Learning
"Deep Learning" methods attempt to learn generic features in an unsuperv...
read it

Composite Binary Losses
We study losses for binary classification and class probability estimati...
read it
Robert C. Williamson
is this you? claim profile