Program Highlights »
Sat Dec 10th 08:00 AM -- 06:30 PM @ Area 1
Bayesian Deep Learning
Yarin Gal · Christos Louizos · Zoubin Ghahramani · Kevin P Murphy · Max Welling

Workshop Home Page

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.

08:30 AM BNNs for RL: A Success Story and Open Questions (Invited talk)
Finale Doshi-Velez
08:55 AM Categorical Reparameterization with Gumbel-Softmax (Contributed talk)
Eric Jang
09:10 AM History of Bayesian neural networks (Keynote talk)
Zoubin Ghahramani
09:40 AM Poster spotlights (Spotlights)
09:55 AM Discussion over coffee and poster session I (Poster Session)
10:55 AM Deep exponential families (Invited talk)
David Blei
11:20 AM Relativistic Monte Carlo (Contributed talk)
11:35 AM Alpha divergence minimization for Bayesian deep learning (Invited talk)
José Miguel Hernández-Lobato
12:00 PM Lunch (Break)
01:30 PM A Tribute to David MacKay (Plenary talk)
Ryan Adams
02:00 PM Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness (Invited talk)
Ian Goodfellow
02:25 PM Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Training (Contributed talk)
02:40 PM Discussion over coffee and poster session II (Poster Session)
03:35 PM Bayesian Agents: Bayesian Reasoning and Deep Learning in Agent-based Systems (Invited talk)
Shakir Mohamed
04:00 PM Panel Discussion
Shakir Mohamed, David Blei, Ryan Adams, José Miguel Hernández-Lobato, Ian Goodfellow, Yarin Gal
05:00 PM Discussion over coffee and poster session III (Poster Session)