`

Timezone: »

 
Workshop
Advances in Approximate Bayesian Inference
Francisco Ruiz · Stephan Mandt · Cheng Zhang · James McInerney · James McInerney · Dustin Tran · Dustin Tran · David Blei · Max Welling · Tamara Broderick · Michalis Titsias

Fri Dec 08 08:00 AM -- 06:30 PM (PST) @ Seaside Ballroom
Event URL: http://approximateinference.org »

Approximate inference is key to modern probabilistic modeling. Thanks to the availability of big data, significant computational power, and sophisticated models, machine learning has achieved many breakthroughs in multiple application domains. At the same time, approximate inference becomes critical since exact inference is intractable for most models of interest. Within the field of approximate Bayesian inference, variational and Monte Carlo methods are currently the mainstay techniques. For both methods, there has been considerable progress both on the efficiency and performance.

In this workshop, we encourage submissions advancing approximate inference methods. We are open to a broad scope of methods within the field of Bayesian inference. In addition, we also encourage applications of approximate inference in many domains, such as computational biology, recommender systems, differential privacy, and industry applications.

Fri 8:30 a.m. - 8:35 a.m.
Introduction (Talk)
Cheng Zhang, Francisco Ruiz, Dustin Tran, James McInerney, Stephan Mandt
Fri 8:35 a.m. - 9:00 a.m.
Invited talk: Iain Murray (TBA) (Talk)
Iain Murray
Fri 9:00 a.m. - 9:15 a.m.
Contributed talk: Learning Implicit Generative Models Using Differentiable Graph Tests (Talk)
Josip Djolonga
Fri 9:15 a.m. - 9:40 a.m.
Invited talk: Gradient Estimators for Implicit Models (Talk)
Yingzhen Li
Fri 9:40 a.m. - 10:00 a.m.
Industry talk: Variational Autoencoders for Recommendation (Talk)
Dawen Liang
Fri 10:00 a.m. - 10:30 a.m.
Poster Spotlights (Spotlight)
Francesco Locatello, Ari Pakman, Da Tang, Tom Rainforth, Zalán Borsos, Marko Järvenpää, Eric Nalisnick, Gabriele Abbati, XIAOYU LU, Jonathan Huggins, Rachit Singh, Rui Luo
Fri 10:30 a.m. - 11:25 a.m.
Coffee Break and Poster Session 1 (Break)
Fri 11:25 a.m. - 11:45 a.m.
Industry talk: Cedric Archambeau (TBA) (Talk)
Cedric Archambeau
Fri 11:45 a.m. - 12:00 p.m.
Contributed talk: Variational Inference based on Robust Divergences (Talk)
Futoshi Futami
Fri 12:00 p.m. - 1:00 p.m.
Lunch Break (Break)
Fri 1:00 p.m. - 2:05 p.m.
Poster Session
Shunsuke Horii, Heejin Jeong, Tobias Schwedes, Qing He, Ben Calderhead, Ertunc Erdil, Jaan Altosaar, Patrick Muchmore, Rajiv Khanna, Ian Gemp, Pengfei Zhang, Yuan Zhou, Chris Cremer, Maria DeYoreo, Alexander Terenin, Brendan McVeigh, Rachit Singh, Yaodong Yang, Erik Bodin, Trefor Evans, Henry Chai, Shandian Zhe, Jeffrey Ling, Vincent ADAM, Lars Maaløe, Andrew Miller, Ari Pakman, Josip Djolonga, Hong Ge
Fri 2:05 p.m. - 2:20 p.m.
Contributed talk: Adversarial Sequential Monte Carlo (Talk)
Kira Kempinska
Fri 2:20 p.m. - 2:35 p.m.
Contributed talk: Scalable Logit Gaussian Process Classification (Talk)
Florian Wenzel
Fri 2:35 p.m. - 3:00 p.m.
Invited talk: Variational Inference in Deep Gaussian Processes (Talk)
Andreas Damianou
Fri 3:00 p.m. - 3:30 p.m.
Coffee Break and Poster Session 2 (Break)
Fri 3:30 p.m. - 3:45 p.m.
Contributed talk: Taylor Residual Estimators via Automatic Differentiation (Talk)
Andrew Miller
Fri 3:45 p.m. - 4:10 p.m.
Invited talk: Differential privacy and Bayesian learning (Talk)
Antti Honkela
Fri 4:10 p.m. - 4:25 p.m.
Contributed talk: Frequentist Consistency of Variational Bayes (Talk)
Yixin Wang
Fri 4:25 p.m. - 5:30 p.m.
Panel: On the Foundations and Future of Approximate Inference (Panel)
David Blei, Zoubin Ghahramani, Katherine Heller, Tim Salimans, Max Welling, Matthew D. Hoffman

Author Information

Francisco Ruiz (Columbia University)
Stephan Mandt (Disney Research)
Cheng Zhang (Microsoft Research, Cambridge)
James McInerney (Spotify Research)
James McInerney (Spotify)
Dustin Tran (Columbia University & OpenAI)
Dustin Tran (Google Brain)
David Blei (Columbia University)

David Blei is a Professor of Statistics and Computer Science at Columbia University, and a member of the Columbia Data Science Institute. His research is in statistical machine learning, involving probabilistic topic models, Bayesian nonparametric methods, and approximate posterior inference algorithms for massive data. He works on a variety of applications, including text, images, music, social networks, user behavior, and scientific data. David has received several awards for his research, including a Sloan Fellowship (2010), Office of Naval Research Young Investigator Award (2011), Presidential Early Career Award for Scientists and Engineers (2011), Blavatnik Faculty Award (2013), and ACM-Infosys Foundation Award (2013). He is a fellow of the ACM.

Max Welling (University of Amsterdam / Qualcomm AI Research)
Tamara Broderick (MIT)
Michalis Titsias (DeepMind)

More from the Same Authors