I’m at NIPS 2017. Please catch me or e-mail me if you’d like to chat about research! I can also describe my experience in the Bayesflow team at Google—TensorFlow meets Bayes which is led by Rif Saurous and partially Kevin Murphy—as well as David Blei’s group at Columbia. Both are always looking for excellent researchers as postdocs, research scientists, and interns.
As advertisement, we’re fortunate to have two posters at the main conference:
- Adji B. Dieng, Dustin Tran, Rajesh Ranganath, John Paisley, David M. Blei (2017). Variational inference via -upper bound minimization. Monday, 06:30 – 10:30 PM @ Pacific Ballroom #186
- Dustin Tran, Rajesh Ranganath, David M. Blei (2017). Hierarchical implicit models and likelihood-free variational inference. Wednesday, 06:30 – 10:30 PM @ Pacific Ballroom #179
At workshops, I’ll also be presenting three talks and two posters:
- Title: Implicit causal models for genome-wide association studies
Friday, 11:40–12:00 @ Room 104 C. NIPS Workshop: Deep Learning for Physical Sciences. - Title: Why Aren’t You Using Probabilistic Programming?
Saturday, 8:05–8:30 @ Hall C. NIPS Workshop: Bayesian Deep Learning. - Title: Lessons learned from designing Edward
Saturday, 8:05–8:30 @ Room 202. NIPS Workshop: NIPS Highlights, Learn How to Code a Paper. - Poster: Implicit causal models for genome-wide association studies [pdf] [arxiv]
Dustin Tran, David M. Blei (2017).
Friday @ Room 104 C. NIPS Workshop: Deep Learning for Physical Sciences. - Poster: Feature-matching auto-encoders [pdf]
Dustin Tran, Yura Burda, Ilya Sutskever (2017).
Saturday @ Hall C. NIPS Workshop: Bayesian Deep Learning.
The NIPS approximate inference workshop will be quite a bit of fun this Friday @ Seaside Ballroom. Join us!
Finally, if you’d like to talk about current research, I’m very excited to talk about the workshop papers and our recent probabilistic programming work: TensorFlow Distributions, and a coming book chapter on deep probabilistic programming with Vikash Mansinghka.
See you at the conference.