Machine Learning talk by Prof. Arthur Gretton
Arthur Gretton is a Professor with the Gatsby Computational Neuroscience Unit, CSML, UCL, which he joined in 2010.
He received degrees in physics and systems engineering from the Australian National University, and a PhD with Microsoft Research and the Signal Processing and Communications Laboratory at the University of Cambridge. He worked from 2002-2012 at the MPI for Biological Cybernetics, and from 2009-2010 at the Machine Learning Department, Carnegie Mellon University.
Arthur's research interests include machine learning, kernel methods, statistical learning theory, nonparametric hypothesis testing, blind source separation, Gaussian processes, and non-parametric techniques for neural data analysis. He has been an associate editor at IEEE Transactions on Pattern Analysis and Machine Intelligence from 2009 to 2013, an Action Editor for JMLR since April 2013, a member of the program committees at NIPS, ICML, COLT conferences.
Representing and comparing probabilities with kernels
I will provide an introduction to kernel tools developed to represent and compare probability distributions. I'll begin by defining a measure of similarity between probability representations, both as a distance between features and as an integral probability metric. I'll then discuss ways of designing kernels or features to make two distributions as distinguishable as possible. The second part of the talk will focus on more sophisticated applications of distribution representations, such as model criticism and testing for independence
The talk is open to everyone interested and we are looking forward to seeing many representatives from OsloMet!
For any inquiries, please contact Valeriya Naumova at Simula.