Call For Papers
Abstract submission deadline: Thu May 16, 2019 20:00 PM UTC ( Countdown:
Full paper submission deadline: Thu May 23, 2019 22:00 PM UTC ( Countdown: )
Submit at: https://cmt3.research.microsoft.com/NeurIPS2019/
The site will start accepting submissions on May 1st.
We invite submissions for the Thirty-Third Annual Conference on Neural Information Processing Systems (NeurIPS 2019), a multi-track, interdisciplinary conference that brings together researchers in machine learning, computational neuroscience, and their applications. You may find the list of the many subject areas covered by the conference here.
The following changes have been put in place this year:
We are introducing a mandatory abstract submission deadline, a week before final submissions are due. Only a submission with a full abstract entered into CMT by May 16, 2019 will be allowed to have the full paper uploaded by May 23, 2019. While it will be possible to edit the title and abstract until the full paper submission deadline, submissions with a “placeholder” title or abstract will be removed without consideration.
It will not be possible to modify the author list of a submission after the full paper submission deadline.
To foster reproducibility, authors will be asked to answer all questions from the following Reproducibility Checklist during the submission process. The answers, which can be updated before the full paper submission deadline, will be made available to the reviewers to help them evaluate the submission. Joelle Pineau will serve as the Reproducibility Chair for NeurIPS-2019, a new role created this year.
We are experimenting with a new code submission policy. This document clarifies this year’s expectations regarding the release of code with the camera ready version of accepted papers that fall under the policy (due on October 27, 2019). In short, we expect (but not require) accompanying code to be submitted with accepted papers that contribute and present experiments with a new algorithm.
As an additional step to make NeurIPS content accessible to those unable to attend the conference, authors of accepted submissions will be required (not optional) to provide a link to at least one of the following accompanying materials for their paper, prior to the conference:
A. 3-minute video summarizing the paper
B. PDF of slides summarizing the paper
C. PDF of the poster used at the conference
Authors will be asked to confirm that their submissions accord with the NeurIPS code of conduct.
Frequently asked questions can be found here.
Formatting instructions: All submissions must be in PDF format. Submissions are limited to eight content pages, including all figures and tables; additional pages containing only references are allowed. You must format your submission using the NeurIPS 2019 LaTeX style file, the style file includes a “preprint” option for non-anonymous preprints posted online. Authors are encouraged to validate their submissions using the NeurIPS submission checker. Please check your submission well in advance of the deadline to avoid server congestion. The maximum file size for submissions is 50MB. Submissions that violate the NeurIPS style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review. If your submission is accepted, you will be allowed a ninth content page for the camera-ready version.
Supplementary material: Authors may submit up to 100MB of supplementary material, such as proofs, derivations, data, or source code; all supplementary material must be in PDF or ZIP format. Supplementary material should be material, created by the authors, that directly supports the submission content. Like submissions, supplementary material must be anonymized. To submit supplementary material, first upload your submission. You will then be able to upload supplementary material from the author console. Looking at supplementary material is at the discretion of the reviewers.
Evaluation criteria: Submissions that violate the NeurIPS style or page limits, are not within the scope of NeurIPS (see subject areas above), are in submission elsewhere, or have already been published elsewhere may be rejected without further review. Submissions that have fatal (confirmed) flaws revealed by the reviewers—including incorrect proofs, flawed or insufficient wet-lab, hardware, or software experiments—may be rejected on that basis, without taking into consideration other criteria. Other submissions will be judged on the basis of their technical quality, novelty, potential impact, and clarity. Typical NeurIPS papers often (but not always) include a mix of algorithmic, theoretical, and experimental results, in varying proportions. While theoretically grounded arguments are encouraged, it is counterproductive to add “decorative math” whose primary purpose is to make the submission look more substantial or even intimidating, without adding significant insight. Algorithmic contributions should have at least an illustration of how the algorithm might eventually materialize into a machine learning application.
Double-blind reviewing: The reviewing process will be double blind at the level of reviewers and area chairs (i.e., reviewers and area chairs cannot see author identities) but not at the level of senior area chairs and program chairs. As an author, you are responsible for anonymizing your submission. In particular, you should not include author names, author affiliations, or acknowledgements in your submission and you should avoid providing any other identifying information (even in the supplementary material). If you need to cite one of your own papers, you should do so with adequate anonymization to preserve double-blind reviewing (e.g., write “In the previous work of Author et al. …” rather than “In our previous work ...”). If you need to cite one of your own papers that is in submission to NeurIPS or elsewhere please do so with adequate anonymization and make sure the cited submission is available for reviewers to read (e.g., if the cited submission is available as a non-anonymous preprint, then write “Author et al.  concurrently show…”; if the cited submission is not available as a non-anonymous preprint, then include a copy of the cited submission in the supplementary material and write “Anonymous et al.  concurrently show...”).
Preprints: Non-anonymous preprints (on arXiv, social media, websites, etc.) are permitted. If you choose to use the NeurIPS style for the preprint, you must use the “preprint” option rather than the “final” option. Reviewers will be instructed not to actively look for such preprints, but encountering them will not constitute a conflict of interest. Authors may submit work to NeurIPS that is already available as a preprint (e.g., on arXiv) without citing it; however, previously published papers by the authors on related topics must be cited (with adequate anonymization to preserve double-blind reviewing).
Dual submissions: Dual submissions will be identified via a combination of automated methods and human (reviewer, area chair, senior area chair, program chair) judgment. NeurIPS coordinates with other conferences to identify dual submissions. Submissions that are identical or substantially similar to papers that are in submission to, have been accepted to, or have been published in other archival conferences, journals, workshops, etc. will be deemed dual submissions. Submissions that are identical or substantially similar to other NeurIPS submissions will also be deemed dual submissions; submissions should be distinct and sufficiently substantial. Note that slicing contributions too thinly may result in submissions being deemed dual submissions. Specifically, a case of slicing too thinly may correspond to two submissions by the same authors that are so similar that publishing one would render the other too incremental to be accepted. The program chairs reserve the right to reject all NeurIPS submissions by all authors of dual submissions, not just those deemed dual submissions. The NeurIPS policy on dual submissions applies for the entire duration of the reviewing process (i.e., from the submission deadline to the notification date). Authors should contact the program chairs if they need further clarification.
Author responses: Authors will have one week to view and respond to initial reviews. This year, all author responses must be in PDF format. Author responses are limited to one page, including all figures, tables, and references, in the NeurIPS “author response” style; you must use the NeurIPS 2019 author response LaTeX style file. Author responses must not contain external links. The program chairs reserve the right to solicit additional reviews after the author response period.
Publication of submissions: After decisions have been made, reviews, meta-reviews, and author responses for accepted submissions will be made public (but reviewer, area chair, and senior area chair identities will remain anonymous). Camera-ready papers will be due in advance of the conference, by October 27th. Authors will have the opportunity to submit code together with their paper, as per the Code Submission Policy. Finally, authors will be allowed to make minor changes, such as fixing typos or adding references, for a short period of time after the conference.
Toronto Paper Matching System: NeurIPS uses the Toronto Paper Matching System (TPMS) in order to assign submissions to reviewers and area chairs. TPMS computes similarity scores between NeurIPS submissions and reviewers’ papers. During the submission process, you will be asked to agree to the use of TPMS for your submission.
Competitions, Demonstrations, Tutorials, and Workshops: There are separate competition and demonstration tracks at NeurIPS 2019. Authors who wish to submit to these tracks should consult the appropriate calls for submission. There are also separate calls for tutorials and workshops.
Alina Beygelzimer, Emily Fox, Florence d’Alché, Hugo Larochelle
NeurIPS 2019 Program Chairs
NeurIPS 2019 General Chair