December 2, 2018
Le 1000 Conference Center
1000 Rue de la Gauchetière Ouest
Montréal, QC H3B 0A2, Canada
| 7:30 - 8:30 | Registration (Coffee will be served) |
| 8:30 - 8:40 | Introduction |
| 8:40 - 9:10 | Invited | David Duvenaud: Self-tuning Gradient Estimators for Discrete Random Variables Slides |
| 9:10 - 9:30 | Contributed | Maria I. Gorinova: Automatic Reparameterisation in Probabilistic Programming Slides |
| 9:30 - 10:00 | Invited | Tamara Broderick: Automated Scalable Bayesian Inference via Data Summarization Slides |
| 10:00 - 11:00 | Coffee Break and Poster Session (Paper IDs 1-24) |
| 11:00 - 11:20 | Contributed | George Tucker: Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives Slides |
| 11:20 - 11:50 | Invited | Tom Rainforth: Inference Trees: Adaptive Inference with Exploration Slides |
| 11:50 - 12:10 | Contributed | David Burt: Explicit Rates of Convergence for Sparse Variational Inference in Gaussian Process Regression Slides |
| 12:10 - 13:40 | Lunch Break (on your own) |
| 13:40 - 14:10 | Invited | Thomas Schon: Sequential Monte Carlo in the machine learning toolbox Slides |
| 14:10 - 14:30 | Contributed | Badr-Eddine Chérief-Abdellatif: Consistency of ELBO maximization for model selection Slides |
| 14:30 - 15:00 | Invited | Sebastian Nowozin: Debiasing Approximate Inference Slides |
| 15:00 - 16:00 | Coffee Break and Poster Session (Paper IDs 25-45) |
| 16:00 - 16:20 | Contributed | Will Grathwohl: Scalable Reversible Generative Models with Free-form Continuous Dynamics Slides |
| 16:20 - 16:50 | Invited | Emtiyaz Khan: Fast yet Simple Natural-Gradient Descent for Variational Inference Slides |
| 16:50 - 17:10 | Contributed | Matthew Hoffman: NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport Slides |
| 17:10 - 18:00 | Panel
Alexander Alemi, David Duvenaud, Kevin Murphy, Ole Winther, Tamara Broderick Moderator: Yingzhen Li |