We invite researchers in machine learning and statistics to participate in
the:

NIPS 2014 Workshop on Advances in Variational Inference

12 or 13 December 2014, Montreal, Canada

www.variationalinference.org

Submission deadline: 9 October 2014

1. Call for participation

We invite researchers to submit their recent work on the development,
analysis, and application of variational inference. Submissions should take
the form of an extended abstract of 2–4 pages in PDF format using the NIPS
style available here
<http://nips.cc/Conferences/2014/PaperInformation/StyleFiles> (author names
do not need to be anonymised). Submissions will be accepted either as
contributed talks or poster presentations. Final versions of the extended
abstract are due by 28 November and will posted on the workshop website.

Abstracts should be submitted by October 9 to [email protected]
.

2. 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:
www.variational inference.org. This workshop is supported by the
International Society for Bayesian Analysis (ISBA), Adobe Creative
Technologies Laboratory, and Google DeepMind.

3. Confirmed speakers

Matt Hoffman

Michalis Titsias

Erik Sudderth

Sylvain Le Corff

Durk Kingma

4. Key Dates

Paper submission: 9 October 2014

Acceptance notification: 23 October

Final paper submission: 28 November

Workshop:  Friday, 12 or Saturday, 13 December


Workshop organisers

Shakir Mohamed (Google DeepMind)

Tamara Broderick (U. California, Berkeley/ MIT)

Charles Blundell (Google Deepmind)

Matt Hoffmann(Adobe Creative Technologies Lab)

David Blei (U. Princeton)

Michael I. Jordan (U. California, Berkeley)
_______________________________________________
uai mailing list
[email protected]
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

Reply via email to