ICLR 2017

This is an old revision of the document!

International Conference on Learning Representations

ICLR is an annual conference sponsored by the Computational and Biological Learning Society

ICLR 2016

ICLR 2016 will be held May 2-4, 2016 in the Caribe Hilton, San Juan, Puerto Rico.


Workshop Track

To submit a 2-3 pages extended abstract (excluding references), please use the openreview site for the ICLR 2016 Workshop Track:


Remember that the use of the Workshop Track ICLR style file is mandatory.

Important: papers that were reviewed in the Conference Track but were recommended to the Workshop Track do not need to be converted into a shorter extended abstract. The only necessary change is to switch to the Workshop Track style files, before submitting to OpenReview.

The deadline for submitting the title, abstract and extended abstract PDF is 2:00 pm Pacific Standard Time, February 18, 2016.

Conference Track

To submit a paper, please use the CMT site for the ICLR 2016 Conference Track:


Remember that the use of the ICLR style file is mandatory.

For conference submissions, if you have supplementary material for the paper, please include it as a separate section following the references, and name it as such.

The deadline for submitting the title, abstract and a preliminary draft of conference contributions is 2:00 pm Pacific Standard Time, November 12, 2015, while the finalized PDF submissions must be entered by 2:00 pm Pacific Standard Time, November 19, 2015. An arXiv link to submissions must also be provided, as early as possible after November 12. See the main page for more details.


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.

The conference follows a recently introduced open reviewing and open publishing publication process, which is explained in further detail here.

Yoshua Bengio & Yann Lecun, General Chairs