ICLR 2019 - Call For Papers

May 6-9, New Orleans

 

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 deep 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 topics such as feature learning, metric learning, compositional modeling, structured prediction, reinforcement learning, and issues regarding large-scale learning and non-convex optimization. The range of domains to which these techniques apply is also very broad, including vision, speech recognition, text understanding, games, music, computational biology, and others.

A non-exhaustive list of relevant topics:

  • unsupervised, semi-supervised, and supervised representation learning

  • representation learning for planning and reinforcement learning

  • metric learning and kernel learning

  • sparse coding and dimensionality expansion

  • hierarchical models

  • optimization for representation learning

  • learning representations of outputs or states

  • theoretical issues in deep learning

  • visualization or interpretation of learned representations

  • implementation issues, parallelization, software platforms, hardware

  • applications in vision, audio, speech, natural language processing, robotics, neuroscience, computational biology, or any other field

The program will include keynote presentations from invited speakers, oral presentations, and posters.

Similarly to last year, submissions will be double blind, meaning that reviewers cannot see author names when performing reviews, and authors cannot see reviewer names. While we will still use OpenReview to host papers and allow for public discussions that can be seen by all, comments that are posted by reviewers will remain anonymous. If someone wants to cite a paper during the review period, OpenReview will provide a BibTeX entry that does not list the authors, but does give the title, year and url. Only at the end of the review period will the authors be revealed. While ICLR is double blind, we will not forbid authors from posting their paper on arXiv or any other public forum.

Authors can revise their paper as many times as needed up to the paper submission deadline. During the review period, authors will not be allowed to revise their paper. Once the review period is over and the rebuttal period begins, authors can revise their paper but a pdfdiff will be done against the submission at the paper submission deadline.  Area chairs and reviewers reserve the right to ignore changes which are significant from the original scope of the paper.

What Is Changing from ICLR 2018?

This year ICLR will not have a separate Workshop Track. All submissions will be to the main conference track. The conference will instead feature a small number of concurrent workshop sessions, which will be run through a separately chaired process similar to other ML venues.

The paper length guidelines are also updated this year (see below).

Submission Instructions

The paper submission deadline is September 27, 2018 - 5:00 pm EST.  By this time, authors are asked to submit their paper to:

https://openreview.net/group?id=ICLR.cc/2019/Conference

The initial paper needs to be submitted by this date; however, authors are encouraged to update their submission as desired after the review period.

Paper length:

  • The recommended paper length is 8 pages, with unlimited additional pages for citations.

  • There will be a strict upper limit of 10 pages.

  • Reviewers will be instructed to apply a higher standard to papers in excess of 8 pages.

  • Authors may use as many pages of appendices (after the bibliography) as they wish, but reviewers are not required to read these.

The goal is to ensure completeness and reproducibility, while still making it possible to review the papers in a reasonable amount of time.  In some cases slightly longer papers are acceptable, for example if the authors need to insert very large figures or tables.  The appropriateness of using additional pages over the recommended length will be judged by reviewers.

Authors are encouraged to participate in the public discussion of their paper, as well as of any other paper submitted to the conference. Submissions and reviews are both anonymous. For detailed instructions about the format of the paper, please visit www.iclr.cc.

Dual Submission Policy

Submissions that are identical (or substantially similar) to versions that have been previously published, or accepted for publication, or that have been submitted in parallel to other conferences or journals, are not allowed and violate our dual submission policy.  However, papers that cite previous related work by the authors and papers that have appeared on non-peered reviewed websites (like arXiv) or that have been presented at workshops (i.e., venues that do not have a publication proceedings) do not violate the policy. The policy is enforced during the whole reviewing process period.

Withdrawing Policy

Authors have the right to withdraw papers from consideration at any time until paper notification. Before the paper submission deadline, if an author withdraws the paper it will be deleted from the OpenReview hosting site. However, after the paper submission deadline, if an author chooses to withdraw, it will remain hosted by OpenReview in a publicly visible "withdrawn papers" section. Like on arXiv, submissions to ICLR cannot be deleted. Withdrawn papers will be de-anonymized right away.

Reviewing Process

  1. Submissions to ICLR are uploaded on OpenReview, which enables public discussion. Official reviews are anonymous and publicly visible.  Anybody who is logged in can post comments that are publicly visible or restrict visibility to reviewers and up, ACs and up, or just PCs. In addition, the author of a comment can decide to post anonymously or not. Login is required before posting any comment.

  2. Authors are encouraged to revise their paper as many times as needed up until the paper submission deadline. Authors can participate in the discussion about their paper, as well as about any other paper submitted to the conference, at any time.

  3. By October 26, 2018, reviewers need to post their full review. Reviews are anonymous and publicly visible in Open Review. Once the reviews are posted, authors are free to make changes to their paper as often as needed.

  4. The rebuttal and discussion period will be from November 8, 2018 until November 21, 2018, where authors can address reviewer comments and make changes to the paper. During this period, a pdfdiff will be applied to compare new changes to the paper against the original submission. Area chairs and reviewers reserve the right to ignore changes that are significantly different from the original paper. In addition, during this period, any submission that is cited will be given an anonymous BibTex entry.

  5. On December 20, 2018, authors will be notified about the acceptance or rejection of their paper. After notification, all BibTex entries will be de-anonymized.

  6. Papers that are not accepted will be considered non-archival, and may be submitted elsewhere (modified or not), although the OpenReview site will maintain the reviews, the comments, and links to the versions submitted to ICLR.

Style files and Templates

To prepare your submission to ICLR 2019, please use the LaTeX style files provided at: