ICLR 2017

This is an old revision of the document!


At the workshop track of ICLR 2017 we solicit the submission of 3 page abstracts. This year, the Workshop Track will focus and favor late-breaking developments, very novel ideas and position papers. Topics covered may include:

  • Unordered List ItemUnsupervised, 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

Extended abstracts submitted to the Workshop Track should be 2-3 pages long, excluding references. These contributions are considered as workshop papers and can be published elsewhere, i.e., they are not subject to the dual submission policy restriction of our conference track papers. Selection of abstracts is performed via a light single-blinded review process. Note that some of the conference submissions that are not accepted to the Conference Track but fit the novelty requirements of this call for abstract, may also be invited to be presented under the Workshop Track.

ICLR Submission Instructions - Workshop Track

By February 17th, 2016, 5:00 PM Eastern Standard time, authors must submit the PDF of their extended abstract to openreview: https://openreview.net/group?id=ICLR.cc/2017/workshop

For more information on preparing your extended abstract, including style files for the Workshop Track, please see:

Acceptance decisions of extended abstract will be sent by March 17th. At least one author of each accepted extended abstract will be required to register to the ICLR event and present their work.