Submission Guidelines

We welcome submissions on (non exhaustive list):

• Techniques for high-dimensional continuous EBMs (e.g. in Vision, Neuroscience) and for discrete EBMs (e.g. in NLP, Biology).

• Probabilistic (e.g. advanced MCMC and variational inference) and non-probabilistic (e.g. contrastive learning) approaches for training EBMs.

• Comparisons, connections and combinations with other ML approaches and frameworks (Autoregressive models, GANs, Variational Auto-Encoders, Reinforcement Learning, ... ).

• Multidisciplinary applications of EBMs to different domains.

• Applications of EBMs to unsupervised, self-supervised and latent models.

• Emerging models of computation exploiting Energy characteristics in physical processes.

• Opinion pieces in favor or against EBMs.
  

Submissions will be between 2 and 6 pages, but may contain an unlimited number of additional pages for references and appendices. Note that reviewers will not be required to read the latter.
We welcome submissions that are work in progress, as well as submissions that are currently under review at other venues, as long as that fits the format above. Submissions should follow ICLR2021 submission format (LaTeX, overleaf).

Submissions will be evaluated by a Programme Committee to be announced later. Accepted papers will be presented during poster sessions, with a few contributed talks. They will be posted on the workshop site, under a non-archival status.

Submission

Submit your papers on CMT by February 24, 2021 at 11:59PM Anywhere on Earth on the following link:

https://openreview.net/group?id=ICLR.cc/2021/Workshop/EBM (Submission start: Jan 21 2021 09:00AM UTC-0)

The review process will be double-blind. Authors should make sure to anonymise their submissions by removing names and affiliations.