Advances in Variational Inference

NIPS 2014 Workshop

13 December 2014  Level 5  Room 510 a

Convention and Exhibition Center, Montreal, Canada

We invite researchers to submit their recent work on the development, analysis, or application of variational inference. Details about the submission process appear below.

Key Dates

Paper submission: 9 October 2014 16 October 2014 [One-week extension!]

Travel award application deadline: 9 October 2014 16 October 2014 [More info]

Acceptance notification: 30 October 5 November

[Note that NIPS Early Registration pricing ends 7 November]

Notification of type of presentation: 17 November

Travel award notification: 17 November

Final paper submission: 28 November 1 December

Workshop: 13 December 

Poster Details

Please keep to size A1 or smaller, in portrait format; that is 841 mm height by 594 mm width. These dimensions deviate from the standard NIPS size due to our constrained poster space; we need the posters to be A1 in order to accommodate the large number of excellent papers.

Extended Abstract Submission Details

A submission should take the form of an extended abstract of 24 pages in PDF format using the NIPS style available here (author names do not need to be anonymized and references may extend as far as needed beyond the 4 page upper limit). If authors' research has previously appeared in a journal, workshop, or conference (including the NIPS 2014 conference), their workshop submission should extend that previous work. Submissions may include a supplement/appendix, but reviewers are not responsible for reading any supplementary material.

Submissions will be accepted either as contributed talks or poster presentations. Final versions of the extended abstract are due by 28 November and will be posted on the workshop website. There will be no published proceedings for this workshop; we hope that authors will find discussion and feedback at the workshop beneficial for developing the research they present, and we encourage authors to submit their resulting work for publication in other venues after the workshop.

Extended abstracts should be submitted by 9 October 16 October to variational[dot]nips2014[at]gmail[dot]com

Workshop Overview

The ever-increasing size of data sets has resulted in an immense effort in machine learning and statistics to develop more powerful and scalable probabilistic models. Efficient inference remains a challenge and limits the use of these models in large-scale scientific and industrial applications. Traditional unbiased inference schemes such as Markov chain Monte Carlo (MCMC) are often slow to run and difficult to evaluate in finite time. In contrast, variational inference allows for competitive run times and more reliable convergence diagnostics on large-scale and streaming data—while continuing to allow for complex, hierarchical modelling. This workshop aims to bring together researchers and practitioners addressing problems of scalable approximate inference to discuss recent advances in variational inference, and to debate the roadmap towards further improvements and wider adoption of variational methods.

The recent resurgence of interest in variational methods includes new methods for scalability using stochastic gradient methods, extensions to the streaming variational setting, improved local variational methods, inference in non-linear dynamical systems, principled regularisation in deep neural networks, and inference-based decision making in reinforcement learning, amongst others. Variational methods have clearly emerged as a preferred way to allow for tractable Bayesian inference. Despite this interest, there remain significant trade-offs in speed, accuracy, simplicity, applicability, and learned model complexity between variational inference and other approximative schemes such as MCMC and point estimation. In this workshop, we will discuss how to rigorously characterise these tradeoffs, as well as how they might be made more favourable. Moreover, we will address other issues of adoption in scientific communities that could benefit from the use of variational inference including, but not limited to, the development of relevant software packages.

The workshop will consist of invited and contributed talks, a spotlight and poster session, and a panel discussion. For more details see: This workshop is supported by the International Society for Bayesian Analysis (ISBA), Adobe Creative Technologies Laboratory, and Google DeepMind.     Google DeepMind