Timezone: »

Unifying Views in Unsupervised Learning
Zoubin Ghahramani

Thu Dec 09 02:00 PM -- 02:30 PM (PST) @

The NIPS community has benefited greatly from Sam Roweis' insights into the connections between different models and algorithms. I will review our work on a unifying' framework for linear Gaussian models, which formed the backbone of the NIPS Tutorial Sam and I gave in 1999. This framework highlighted connections between factor analysis, PCA, mixture models, HMMs, state-space models, and ICA, had the EM algorithm as the all-purpose swiss-army-knife of learning algorithms, and culminated in agraphical model for graphical models' depicting the connections. Though perhaps well-known now, those connections were surprising at the time (at least to us) and resulted in a more coherent and systematic view of statistical machine learning that has endured to this day. Inspired by this approach, I will present some newer unifying views, of kernel methods, and of nonparametric Bayesian models.

Author Information

Zoubin Ghahramani (Uber and University of Cambridge)

Zoubin Ghahramani is Professor of Information Engineering at the University of Cambridge, where he leads the Machine Learning Group. He studied computer science and cognitive science at the University of Pennsylvania, obtained his PhD from MIT in 1995, and was a postdoctoral fellow at the University of Toronto. His academic career includes concurrent appointments as one of the founding members of the Gatsby Computational Neuroscience Unit in London, and as a faculty member of CMU's Machine Learning Department for over 10 years. His current research interests include statistical machine learning, Bayesian nonparametrics, scalable inference, probabilistic programming, and building an automatic statistician. He has held a number of leadership roles as programme and general chair of the leading international conferences in machine learning including: AISTATS (2005), ICML (2007, 2011), and NIPS (2013, 2014). In 2015 he was elected a Fellow of the Royal Society.

More from the Same Authors