Home / Events / Gaussian and non-Gaussian universality, with applications to data augmentation Note unusual location
Statistics Seminar

Gaussian and non-Gaussian universality, with applications to data augmentation Note unusual location

With Peter Orbanz (UCL)

Gaussian and non-Gaussian universality, with applications to data augmentation

The term Gaussian universality refers to a class of results that are, loosely speaking, generalized central limit theorems (where, somewhat confusingly, the limit law is not necessarily Gaussian). They provide useful tools to study certain problems in machine learning. I will give a short overview of this idea and then present two types of results: One are upper and lower bounds that map out where Gaussian universality is applicable and what rates of convergence one can expect. The other is the use of these techniques to obtain quantitative results on the effects of data augmentation in machine learning problems.

Note unusual location

Add to your calendar or Include in your list