International Conference on Machine Learning June 26–July 1, 2012 — Edinburgh, Scotland

Author instructions

Instructions to presenters

All talks will be video-taped. You need to give permission for your talk to be available on the web after ICML, filling in the video release form.

Long talks should be 17 min + 2 min questions + 1 min switch. Short talks should be 4 min + 1 min switch. You should practice your talk carefully. Please go to your room 10-15 min before your session to meet the session chair, and try out the AV. Rooms will be equipped with standard projectors, as well as a Windows-PC for those who don't have their own laptop.

Each presentation is accompanied by a poster, on the same day as the talk. Poster sessions start at 5:40pm. Posters should follow the A0-landscape format. Poster boards will be numbered, see the program booklet (distributed at the registration desk) to know your poster board number. Please remove your poster after the session. Any posters that remain after 10am on the next day will be discarded.


Papers are limited to 8 pages and 10MB. Detailed instructions for preparing the paper can be found in the following example paper: example_paper.pdf

You may also wish to download the following archive, which contains LaTeX style files and a Word template:

Submissions that exceed the page limits or do not conform to the specified format (in particular if a more compressed format is used) will be rejected without review.

Double-Blind Reviewing

Reviewing for ICML 2012 is double-blind; i.e., reviewers will not know the authors' identity (and vice versa). Detailed instructions for how to ensure your anonymity are also contained in the above example paper. In brief, please refer to your prior work in the third person wherever possible. If you need to make an anonymous reference (e.g., if you refer to your own work that is under review elsewhere), please upload this work as supplementary material (see below). Note that anonymizing your paper is obligatory, and papers that explicitly or implicitly reveal the authors' identities may be rejected. A reviewer may be able to deduce the authors' identities by using external resources, such as technical reports published on the web. The availability of information on the web that may allow reviewers to infer the authors' identities does not constitute a breach of the double-blind submission policy.

Supplementary Material

ICML 2012 supports the submission of supplementary material, such as software, videos, or data sets. In particular, if you make anonymous references in the paper, please upload the referenced papers, so that the reviewers can take a quick look. Please also take care not to reveal your identity in the supplementary material.

However, note that submitted papers must be entirely self-contained. Reviewers are encouraged, but not obliged to look at the provided supplementary material because we also do not want to burden reviewers unnecessarily. In particular, you must not use supplementary material for extending the lengh of your paper. If there is material that you believe is critical to the evaluation of your paper, it needs to be included in the paper.

Supplementary material will not be published or archived. If you want to include it in a final version of the paper, you must put it on a web site and reference the site in the final version of your paper.

Microsoft provides a somewhat unwieldy documentation.

Reviewer Matching

To aid in finding good reviewers for your paper, we will be receiving help from the Toronto Paper Matching System.

As part of the submission process, you will be asked to provide permission to transfer your paper to the "Toronto Paper Matching service", which you should accept.

Double Submission Policy

ICML 2012 will not accept any paper for publication that is substantially similar to another paper that is currently under review or has already been accepted for publication in a journal or another conference. Note that we do have a 'not for publication' submission option which covers some of these cases—see the double submission guide for details.

Please clearly indicate in the submission which contributions are novel and which are previous work, either by the authors or others. If a paper submitted to ICML 2012 and another already published or already submitted paper contain substantial overlap in content and this overlap is not clearly indicated (anonymously) as being previous work, then the ICML submission may be rejected on the grounds of being a dual submission. Similarly, authors must withdraw their papers if they submit an overlapping paper elsewhere during the ICML review period. For papers published in substantially disjoint communities (for example, area conferences where ML is often a core technology), the amount of novel content a paper needs to contain may be less, as long as the submitted papers are themselves clearly targeted to a machine-learning audience.

For more details, see the ICML double submission guide.