International Conference on Learning Representations

{{Short description|Academic conference in machine learning}}

{{Infobox academic conference

| title = International Conference on Learning Representations

| logo = International Conference on Learning Representations.svg

| abbreviation = ICLR

| discipline = Machine learning, artificial intelligence, feature learning

| publisher =

| history = 2013–present

| frequency = Annual

| website = https://iclr.cc/

| openaccess = yes (on openreview.net)

}}

{{Machine learning|Machine-learning venues}}

The International Conference on Learning Representations (ICLR) is a machine learning conference typically held in late April or early May each year. Along with NeurIPS and ICML, it is one of the three primary conferences of high impact in machine learning and artificial intelligence research.{{Cite web |title=Artificial Intelligence - Google Scholar Metrics |url=https://scholar.google.es/citations?view_op=top_venues&hl=en&vq=eng_artificialintelligence |access-date=2024-07-10 |website=scholar.google.es}}

The conference includes invited talks as well as oral and poster presentations of refereed papers. Since its inception in 2013, ICLR has employed an open peer review process to referee paper submissions (based on models proposed by Yann LeCun{{cite web|url=http://yann.lecun.com/ex/pamphlets/publishing-models.html|title=Proposal for A New Publishing Model in Computer Science|website=yann.lecun.com}}). In 2019, there were 1591 paper submissions, of which 500 accepted with poster presentations (31%) and 24 with oral presentations (1.5%).{{cite web|url=https://openreview.net/group?id=ICLR.cc/2019/Conference|title=ICLR 2019 Conference|website=openreview.net}} In 2021, there were 2997 paper submissions, of which 860 were accepted (29%).{{cite web|url=https://openreview.net/group?id=ICLR.cc/2021/Conference|title=ICLR 2021 Conference|website=openreview.net}}