Timezone: »

Bayesian Deep Learning
Yarin Gal · Christos Louizos · Zoubin Ghahramani · Kevin Murphy · Max Welling

Fri Dec 09 11:00 PM -- 09:30 AM (PST) @ Area 1
Event URL: http://bayesiandeeplearning.org/ »

While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor take advantage of the well studied tools of probability theory. This has started to change following recent developments of tools and techniques combining Bayesian approaches with deep learning. The intersection of the two fields has received great interest from the community over the past few years, with the introduction of new deep learning models that take advantage of Bayesian techniques, as well as Bayesian models that incorporate deep learning elements.

In fact, the use of Bayesian techniques in deep learning can be traced back to the 1990s', in seminal works by Radford Neal, David MacKay, and Dayan et al.. These gave us tools to reason about deep models confidence, and achieved state-of-the-art performance on many tasks. However earlier tools did not adapt when new needs arose (such as scalability to big data), and were consequently forgotten. Such ideas are now being revisited in light of new advances in the field, yielding many exciting new results.

This workshop will study the advantages and disadvantages of such ideas, and will be a platform to host the recent flourish of ideas using Bayesian approaches in deep learning and using deep learning tools in Bayesian modelling. The program will include a mix of invited talks, contributed talks, and contributed posters. Also, the historic context of key developments in the field will be explained in an invited talk, followed by a tribute talk to David MacKay's work in the field. Future directions for the field will be debated in a panel discussion.

Fri 11:30 p.m. - 11:55 p.m.
BNNs for RL: A Success Story and Open Questions (Invited talk)
Finale Doshi-Velez
Fri 11:55 p.m. - 12:10 a.m.
Categorical Reparameterization with Gumbel-Softmax (Contributed talk)
Eric Jang
Sat 12:10 a.m. - 12:40 a.m.
History of Bayesian neural networks (Keynote talk)
Zoubin Ghahramani
Sat 12:40 a.m. - 12:55 a.m.
Poster spotlights (Spotlights)
Sat 12:55 a.m. - 1:55 a.m.
Discussion over coffee and poster session I (Poster Session)
Sat 1:55 a.m. - 2:20 a.m.
Deep exponential families (Invited talk)
David Blei
Sat 2:20 a.m. - 2:35 a.m.
Relativistic Monte Carlo (Contributed talk)
Sat 2:35 a.m. - 3:00 a.m.
Alpha divergence minimization for Bayesian deep learning (Invited talk)
José Miguel Hernández-Lobato
Sat 3:00 a.m. - 4:30 a.m.
Lunch (Break)
Sat 4:30 a.m. - 5:00 a.m.
A Tribute to David MacKay (Plenary talk)
Ryan Adams
Sat 5:00 a.m. - 5:25 a.m.
Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness (Invited talk)
Ian Goodfellow
Sat 5:25 a.m. - 5:40 a.m.
Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Training (Contributed talk)
Sat 5:40 a.m. - 6:35 a.m.
Discussion over coffee and poster session II (Poster Session)
Sat 6:35 a.m. - 7:00 a.m.
Bayesian Agents: Bayesian Reasoning and Deep Learning in Agent-based Systems (Invited talk)
Shakir Mohamed
Sat 7:00 a.m. - 8:00 a.m.
Panel Discussion
Shakir Mohamed, David Blei, Ryan Adams, José Miguel Hernández-Lobato, Ian Goodfellow, Yarin Gal
Sat 8:00 a.m. - 10:00 a.m.
Discussion over coffee and poster session III (Poster Session)

Author Information

Yarin Gal (University of Oxford)
Christos Louizos (University of Amsterdam)
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.

Kevin Murphy (Google)
Max Welling (University of Amsterdam and University of California Irvine and CIFAR)

More from the Same Authors