The Tenth International Conference on Learning Representations (Virtual)
Mon Apr 25th through Fri the 29th


ICLR 2022 will host an inaugural blog post track, and is now accepting submissions. For details, see the Call for Blog Posts, and the organizers' post on Blog Posts as Conference Contributions – ICLR Blog.

ICLR 2022 Call For Blog Posts »

Important Dates

Conference Sessions and Workshops Mon Apr 25th through Fri the 29th
Abstract Submission Deadline Sep 29 '21 12:00 AM UTC *
Paper Submission deadline Oct 06 '21 12:00 AM UTC *
WorkshopApplicationDeadline Oct 29 '21 10:00 PM UTC *
Paper Reviews Released Nov 09 '21 07:59 AM UTC *
Author / Reviewer / AC Discussion Period Ends Nov 22 '21(Anywhere on Earth)
Workshop Acceptance Notifications Dec 05 '21 10:00 PM UTC *
Paper Decision Notification Jan 24 '22 11:59 AM UTC *
Registration Opens Feb 02 '22 02:00 PM UTC *
Suggested Submission Date for Workshop Contributions Feb 26 '22 12:00 AM UTC *
Workshop Mandatory Accept/Reject Notification Date Mar 26 '22 01:00 AM UTC *
Registration Cancellation Refund Deadline Apr 12 '22 03:00 PM UTC *
All dates »

Timezone: »


The generous support of our sponsors allowed us to reduce our ticket price by about 50%, and support diversity at the meeting with travel awards. In addition, many accepted papers at the conference were contributed by our sponsors.

Become a 2022 Sponsor »(not currently taking applications)


2022 ICLR Organizing Committee

General Chair

  • Katja Hofmann, Microsoft

Senior Program Chair

  • Yan Liu, University of Southern California

Program Chairs

  • Chelsea Finn, Stanford University
  • Yejin Choi, University of Washington / AI2
  • Marc Deisenroth, University College London

Workshop Chairs

  • Feryal Behbahani, DeepMind
  • Vukosi Marivate, University of Pretoria

Area Chairs

Ethics Review Committee

  • Thomas G. Dietterich, Oregon State University
  • Ayanna Howard, Ohio State University 
  • Patrick Lin, California Polytechnic State University
  • Miguel Luengo-Oroz, UN Global Pulse
  • Shannon Vallor, University of Edinburgh
  • Robert Sparrow, Monash University

Diversity Equity & Inclusion Chairs

  • Krystal Maughan, University of Vermont
  • Rosanne Liu, Google & ML Collective

Virtual Chairs - Virtual & Volunteers 

  • Coming soon

Engagements Chairs - Socials & Sponsors

  • Ehi Nosakhare, Microsoft
  • William Agnew, University of Washington

Blog Track Chairs

  • Sebastien Bubeck, Microsoft
  • David Dobre, MILA
  • Charlie Gauthier, MILA
  • Gauthier Gidel, MILA
  • Claire Vernade, DeepMind

Workflow Chairs

  • Zhenyu (Sherry) Xue
  • Yaguang Li, Google Brain


The organizers can be contacted here.

About Us

The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning.

ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

Participants at ICLR span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

A non-exhaustive list of relevant topics explored at the conference include:

  • unsupervised, semi-supervised, and supervised representation learning
  • representation learning for planning and reinforcement learning
  • representation learning for computer vision and natural language processing
  • 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 audio, speech, robotics, neuroscience, computational biology, or any other field
  • societal considerations of representation learning including fairness, safety, privacy