Department of Statistics & Data Science Seminar

  • Professor, Gatsby Computational Neuroscience Unit
  • Centre for Computational Statistics and Machine Learning
  • University College London

The Maximum Mean Discrepancy for Training Generative Adversarial Networks

Generative adversarial networks (GANs) use neural networks as generative models, creating realistic samples that mimic real-life reference samples (for instance, images of faces, bedrooms, and more). These networks require an adaptive critic function while training, to teach the networks how to move improve their samples to better match the reference data.   I will describe a kernel divergence measure, the maximum mean discrepancy, which represents one such critic function. With gradient regularisation, the MMD is used to obtain current state-of-the art performance on challenging image generation tasks,  including 160 × 160 CelebA and 64 × 64 ImageNet.  In addition to adversarial network training, I'll discuss issues of gradient bias for GANs based on integral probability metrics, and mechanisms for benchmarking GAN performance. 

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 previously worked  at the MPI for Biological Cybernetics, and at the Machine Learning Department, Carnegie Mellon University.

Arthur's research interests include machine learning, kernel methods, statistical learning theory, nonparametric hypothesis testing, and generative models. 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 NIPS Program Committee in 2008 and 2009, a Senior Area Chair for NIPS in 2018, an Area Chair for ICML in 2011 and 2012, and a member of the COLT Program Committee in 2013. Arthur was co-chair of AISTATS in 2016 (with Christian Robert), and co-tutorials chair of ICML in 2018 (with Ruslan Salakhutdinov).


For More Information, Please Contact: 
Catherine Copetas,