ICLR 2016 : ICLR 2016 : International Conference on Learning Representations 2016
Call For Papers
It is well understood that the performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. The rapidly developing field of representation learning is concerned with questions surrounding how we can best learn meaningful and useful representations of data. We take a broad view of the field, and include in it topics such as deep learning and feature learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization.
Despite the importance of representation learning to machine learning and to application areas such as vision, speech, audio and NLP, there was no venue for researchers who share a common interest in this topic. The goal of ICLR has been to help fill this void.
A non-exhaustive list of relevant topics:
- unsupervised, semi-supervised, and supervised representation learning
- metric learning and kernel learning
- dimensionality expansion
- sparse modeling
- hierarchical models
- optimization for representation learning
- learning representations of outputs or states
- implementation issues, parallelization, software platforms, hardware
- applications in vision, audio, speech, natural language processing, robotics, neuroscience, or any other field
The program will include keynote presentations from invited speakers, oral presentations, and posters.
As usual, ICLR will feature two tracks: a Conference Track and a Workshop Track. However, this year, conference and workshop submissions will be reviewed separately, in two different periods. This call for paper is thus only for conference contributions. Workshop submissions will be received a few months before the conference and be subject to a lighter review. A future call for papers will be sent with more details on the Workshop Track.
Also, the reviewing period for conference submissions will be separated into two short rounds (normally 2 reviews in the first round, 1 review in the second round). The first round will run as usual. The second round reviews, however, in addition to evaluating the submissions, will be required to include comments on the content of the first round reviews. By asking for such comments, we hope to ensure a minimum of discussion for every paper, and favour interactions that might either identify factual errors early or reveal a clearer consensus.
Note that some of the submitted papers that are not accepted to the Conference Track will be invited to be presented under the Workshop Track.
ICLR Submission Instructions
1. By November 12th, authors are asked to enter in openreview.net the title, abstract and author list for their paper.
2. Then, as soon as possible, authors must post on arXiv their submission: http://arxiv.org .
3. Finally, by November 19th, authors must update their submission in openreview.net with the arXiv ID of their paper.
Note that there can be up to 3 days of delay between sending a manuscript on arXiv and receiving your arXiv ID. It is thus important to post your submission on arXiv early. Note also that you can always update your submission on arXiv later on, anytime during the review process. Submissions without an arXiv ID after November 19th will be automatically removed from openreview.net.
For more information on paper preparation, including style files and the URL for the openreview ICLR 2016 website, please see http://www.iclr.cc/doku.php?id=iclr2016:main
Submission deadline: November 12th for title and abstract, November 19th for arXiv ID.
i. Regarding the conference submission's 6-9 page limits, these are really meant as guidelines and will not be strictly enforced. For example, figures should not be shrunk to illegible size to fit within the page limit. However, in order to ensure a reasonable workload for our reviewers, papers that go beyond the 9 pages should be formatted to include a 9 page submission, with supplementary material appended at the end of the manuscript and clearly marked as an appendix, which will be optionally reviewed.
ii. Paper revisions will be permitted, and in fact are encouraged, in response to comments from and discussions with the reviewers (see "An Open Reviewing Paradigm" below).
An Open Reviewing Paradigm
1. Submissions to ICLR are posted on arXiv prior to being submitted to the conference.
2. Authors submit their paper to either the ICLR conference track or workshop track via the openreview.net ICLR 2016 website.
3. After the authors have submitted their papers via openreview.net, the ICLR program committee designates anonymous reviewers as usual.
4. The submitted reviews are published without the name of the reviewer, but with an indication that they are the designated reviews.
5. Anyone can openly (non-anonymously) write and publish comments on the paper. Anyone can ask the program chairs for permission to become an anonymous designated reviewer (open bidding). The program chairs have ultimate control over the publication of each anonymous review. Open commenters will have to use their real names.
6. Authors can post comments in response to reviews and comments. They can revise the paper as many times as they want, possibly citing some of the reviews. Reviewers are expected to revise their reviews in light of paper revisions.
7. The review calendar includes a generous amount of time for discussion between the authors, anonymous reviewers, and open commentators. The goal is to improve the quality of the final submissions.
8. The ICLR program and area chairs will consider all submitted papers, comments, and reviews and will decide which papers are to be presented in the conference track, which will be invited to be presented in the workshop track, and which will not appear at ICLR.
9. Papers that are presented in the workshop track or are not accepted will be considered non-archival, and may be submitted elsewhere (modified or not), although the ICLR site will maintain the reviews, the comments, and the links to the arXiv versions.
Yoshua Bengio, Université de Montreal, General Chair
Yann LeCun, New York University and Facebook, General Chair
Hugo Larochelle, Twitter and Université de Sherbrooke, Senior Program Chair
Brian Kingsbury, IBM Watson Group, Program Chair
Samy Bengio, Google, Program Chair
The organizers can be contacted at firstname.lastname@example.org