Bayesiandeeplearning.org Website Review

Friday, December 7, 2018 — Palais des Congrès de Montréal, Montréal, Canada INVITED SPEAKERS This year's theme is the use of de*p learning uncertainty in real-world applications, with speakers working on Challenges at the confluence of de*p learning and probabilistic programming Dmitry Vetrov (Samsung AI centre) (Semi-)Implicit Modeling as New De*p Tool for Approximate Bayesian Matthias Bauer and Andriy Mnih Resampled Priors for Variational Autoencoders Debora Marks (Harvard Medical School) Generative de*p models for challenging biological problems Harri Valpola (Curious AI Company) Estimating uncertainty for model-based reinforcement learning Christian Leibig (Tuebingen) Leveraging (Bayesian) uncertainty information: opportunities and Dan Rosenbaum, Frederic Besse, Fabio Viola, Danilo Rezende and Ali Eslami Learning models for visual 3D localization with implicit mapping Balaji Lakshminarayanan (De*pMind) Probabilistic model ensembles for predictive uncertainty estimation Sergey Levine (Berkeley) Control as Inference: a Connection Between Reinforcement Learning Frank Soboczenski, Michael D. Himes, Molly D. O'Beirne, Simone Zorzan, Atılım Günes Baydin, Adam D. Cobb, Daniel Angerhausen, Giada N. Arney and Shawn D. Domagal-Goldman Bayesian De*p Learning for Exoplanet Atmospheric Retrieval Yashar Hezaveh (Stanford) Mapping the most distant galaxies of the universe with Bayesian Tim Genewein (Bosch Center for AI) A Bayesian view on neural network compression David Sontag (MIT) Bayesian de*p learning for healthcare Hyunjik Kim, Andriy Mnih, Jonathan Schwarz, Marta Garnelo, Ali Eslami, Dan Rosenbaum, Oriol Vinyals and Yee Whye Teh Yarin Gal (Oxford) Bayesian De*p Learning in Self-Driving Cars (and more) Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander Alemi and George Tucker Gintare Karolina Dziugaite, Gabriel Arpino and Daniel Roy TOWARDS GENERALIZATION GUARANTEES FOR SGD: DATA-DEPENDENT PAC-BAYES