TADGM 2018: Theoretical Foundations and Applications of Deep Generative Models Stockholm, Sweden, July 14-15, 2018 |
Conference website | http://sites.google.com/view/tadgm |
Submission link | https://easychair.org/conferences/?conf=tadgm2018 |
Submission deadline | May 31, 2018 |
ICML2018 workshop on Theoretical Foundations and Applications of Deep Generative Models
Co-located with ICML 2018 conference, Stockholm, Sweden
Date: July 14-15 (TBD), 2018 (submission deadline: May 31, 2018)
Workshop Home Page: https://sites.google.com/view/tadgm
Overview
In recent years there has been resurgence of interest in deep generative models (DGMs). The emerging approaches, such as VAEs, GANs, GMMNs, auto-regressive neural networks, and many of their variants and extensions, have led to impressive results in a myriad of applications, such as image generation and manipulation, text generation, disentangled representation learning, and semi-supervised learning. In fact, research on DGMs has a long history. Early forms of such models date back to works on hierarchical Bayesian models and neural network models such as Helmholtz machines, originally studied in the context of unsupervised learning and latent space modeling. Despite recent advances, many foundational aspects of deep generative models are relatively unexplored, including theoretical properties, effective algorithms for learning and inference, and deployment in real-world applications. This workshop aims to be a platform for exchanging ideas regarding both theoretical foundations and applications of DGMs, identifying key challenges in the field, and establishing the most exciting future directions for research into DGMs.
Submission Guidelines
We invite the submission of full 6-8 page papers, with unlimited space for references and supplementary materials. The submissions should follow the ICML 2018 style and formatting guidelines. Authors can include their identities in submissions.
Papers can be submitted at the address: https://easychair.org/conferences/?conf=tadgm2018
Relevant topics include but are not limited to:
- Theoretical understanding
- Formal connections between different DGMs
- Formal connections between DGMs and techniques in other fields, such as Bayesian inference, probabilistic graphical models, reinforcement learning, etc
- Optimization, learning, and Bayesian inference
- Evaluation methods
- Empirical analyses, applications and practical implementations
Submissions will be accepted as contributed talks or poster presentations. Accepted papers will be posted on the workshop website, and have the option of inclusion in the workshop proceeding. Accepted papers are free to appear in journals or conference proceedings.
We will award a best-paper prize selected by our program committee.
- Paper submissions due: May 31, 2018
- Acceptance notification: June 14, 2018
- Workshop: July 14-15 (TBD), 2018
Invited Speakers
- Yoshua Bengio (University of Montreal)
- Kamalika Chaudhuri (University of California, San Diego)
- Arthur Gretton (University College London)
- Pushmeet Kohli (DeepMind)
- Honglak Lee (University of Michigan, Google)
- Juergen Schmidhuber (IDSIA)
- Eric Xing (CMU, Petuum)
[more to be announced!]
Workshop Organizers
- Zhiting Hu (Carnegie Mellon University, Petuum Inc.)
- Andrew Gordon Wilson (Cornell University)
- Ruslan Salakhutdinov (Carnegie Mellon University)
- Eric P. Xing (Carnegie Mellon University, Petuum Inc.)