David Blei, Ian Goodfellow, Balaji Lakshminarayanan, Shakir Mohamed, Rajesh Ranganath, and I are organizing a workshop at ICML this year, titled “Implicit Models”.
Workshop URL: https://sites.google.com/view/implicitmodels/
Leveraging this recent and highly impactful topic, I’m personally excited to see how we might foster discussion across communities. (See the bibliography page for detailed references.)
The deadline for paper submissions (including travel awards) is June 30, 2017.
Probabilistic models are an important tool in machine learning. They form the basis for models that generate realistic data, uncover hidden structure, and make predictions. Traditionally, probabilistic models in machine learning have focused on prescribed models. Prescribed models specify a joint density over observed and hidden variables that can be easily evaluated. The requirement of a tractable density simplifies their learning but limits their flexibility — several real world phenomena are better described by simulators that do not admit a tractable density. Probabilistic models defined only via the simulations they produce are called implicit models.
Arguably starting with generative adversarial networks, research on implicit models in machine learning has exploded in recent years. This workshop’s aim is to foster a discussion around the recent developments, commonalities among applications, and future directions of implicit models.
We invite submission of papers for poster and short oral presentations. Topics of interest include but are not limited to:
-
implicit models,
-
generative adversarial networks,
-
adversarial training,
-
variational inference with implicit approximations,
-
approximate Bayesian computation,
-
likelihood free inference,
-
two sample testing and density ratio estimation,
-
theory,
-
evaluation and
-
applications of implicit models.
Key Dates:
-
June 30, 2017: Submission and Travel Award Deadline
-
July 14, 2017: Acceptance and Travel Award Notification
-
Aug 1, 2017: Final papers due
-
Aug 10, 2017: Workshop date
Submission Instructions: Researchers interested in contributing should upload a short paper of 4 pages in PDF format by June 30, 2017, 11:59pm (time zone of your choice) to the submission web site https://sites.google.com/view/implicitmodels/submissions. References and supplementary material can exceed 4 pages.
Authors should use the ICML style file. Submissions don’t need to be anonymized. The workshop allows submissions of papers that are under review or have been recently published in a conference or a journal. Authors should state any overlapping published work at time of submission.
All submissions will be reviewed and will be evaluated on the basis of their technical content. Accepted papers will selected for either a short oral presentation or spotlight presentation, in addition to poster presentation.
If you have any questions, please contact us at implicitmodels2017@gmail.com.
Confirmed Speakers:
-
Sanjeev Arora (Princeton)
-
Stefano Ermon (Stanford)
-
Qiang Liu (Dartmouth)
-
Kerrie Mengerson (Queensland University of Technology)
-
Dougal Sutherland (UCL)