posted by user: lixxin || 4979 views || tracked by 78 users: [display]

ICLR 2017 : 5th International Conference on Learning Representations


When Apr 24, 2017 - Apr 26, 2017
Where Palais des Congrès Neptune, Toulon, Fr
Submission Deadline Nov 4, 2016
Notification Due Dec 16, 2016
Final Version Due Feb 3, 2017
Categories    machine learning   deep learning   learning representation

Call For Papers

Call For Papers

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 topics such as deep learning and 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, from vision to speech recognition, text understanding, gaming, music, etc.

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
- 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.

ICLR features two tracks: a Conference Track and a Workshop Track. Submissions of extended abstracts to the Workshop Track will be accepted after the decision notifications for Conference Track submissions are sent. A future call for extended abstracts will provide more details on the Workshop Track. Some of the submitted Conference Track papers that are not accepted to the conference proceedings will be invited for presentation in the Workshop Track.
What Is Changing From ICLR 2016

We will use OpenReview (as opposed to CMT) for the Conference Track. Moreover, submissions will be hosted by OpenReview (no requirement to submit to arXiv). We will have a two-round review process. In the first round, reviewers may only ask clarification questions. The program committee will select best review awards. Corresponding reviewers will be placed in the pool for candidate ACs for ICLR 2018. The Workshop Track will favor highly innovative, but possibly not fully validated, submissions.

The goal is to improve the quality of the overall reviewing process. By using OpenReview, authors can update their paper respond to comments anytime. Also, anybody in the community can comment on submissions and reviewers can leverage public discussions to improve their understanding and rating of papers.
Submission Instructions

By November 4th (5:00pm Eastern Standard Time - EST) authors are asked to submit their paper to:

The submission deadline will be strictly enforced. There is no strict limit on paper length. However, we strongly recommend keeping the paper at 8 pages, plus 1 page for the references and as many pages as needed in an appendix section (all in a single pdf). The appropriateness of using additional pages over the recommended length will be judged by reviewers. Authors are encouraged to update their submission as desired and participate in the public discussion of their paper, as well as any other paper submitted to the conference. Submissions are not anonymous, but reviews will be anonymized. For detailed instructions about the format of the paper, please visit
Reviewing Process

Submissions to ICLR are uploaded on OpenReview, which enables public discussion. All comments are publicly visible (even for people who are not logged in) but the author of a comment can decide to post anonymously or not. Log in is required before posting any comment.
Authors are encouraged to revise their paper as many times as needed and, anytime, to participate in the discussion about their paper as well as any other paper submitted to the conference.
By December 2nd 2016, reviewers need to post questions for papers assigned to them. Reviews are anonymous and publicly visible in OpenReview.
By December 16th 2016, reviewers need to post their full review. Again, reviews are anonymous and publicly visible.
On February 3rd 2016, authors will be notified about the acceptance or rejection of their paper. Some of the rejected papers that distinguish themselves for their originality will be invited for presentation under the Workshop Track.
Papers that are not accepted to the Conference Track or presented to the Workshop track 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 2017, please use the LaTeX style files provided below, choosing the appropriate files for the track you are submitting to:

Conference Track:

Workshop Track:

Related Resources

ICML 2017   34th International Conference on Machine Learning
ICLR 2016   ICLR 2016 : International Conference on Learning Representations 2016
IJCAI 2017   International Joint Conference on Artificial Intelligence
MLDM 2017   Machine Learning and Data Mining in Pattern Recognition
DSAA 2017   The 4th IEEE International Conference on Data Science and Advanced Analytics 2017
ECML-PKDD 2017   European Conference on Machine Learning and Principles and Practice of Knowledge Discovery
PAKDD 2017   The 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining
ISMIS 2017   23rd International Symposium on Methodologies for Intelligent Systems
CCML 2017   The 16th China Conference on Machine Learning
ICMR 2017   ACM International Conference on Multimedia Retrieval