@ ICML 2023 in Hawaii, USA on Saturday, July 29th 

Localized Learning Workshop

Decentralized Model Updates via Non-Global Objectives

See https://icml.cc/virtual/2023/workshop/21484  for the content and videos of the workshop!



Topics: Any aspect of localized learning broadly defined.

Paper submission deadline: Wednesday, May 24, 2023 EXTENDED TO Monday, May 29, 2023 (11:59pm AOE)

Format: 4 page papers in ICML format or already accepted papers in original format.

Awards: Outstanding contributed papers (2-3) will receive a free workshop registration.

Submission site: OpenReview 

Camera-ready:  Camera-ready icml2023.sty file (up to 8 pages of content excluding references and appendices)


Despite being widely used, global end-to-end learning has several key limitations. It requires centralized computation, making it feasible only on a single device or a carefully synchronized cluster. This restricts its use on unreliable or resource-constrained devices, such as commodity hardware clusters or edge computing networks. As the model size increases, synchronized training across devices will impact all types of parallelism. 

Global learning also requires a large memory footprint, which is costly and limits the learning capability of single devices. Moreover, end-to-end learning updates have high latency, which may prevent their use in real-time applications such as learning on streaming video. 

Finally, global backpropagation is thought to be biologically implausible, as biological synapses update in a local and asynchronous manner. To overcome these limitations, this workshop will delve into the fundamentals of localized learning, which is broadly defined as any training method that updates model parts through non-global objectives.


Relevant topics include but are not limited to:

Submission Instructions

We welcome submissions of original research papers, work-in-progress reports, and position papers on any aspect of localized learning. The submissions should be in anonymous ICML format with a maximum length of 4 pages with unlimited pages for references and supplementary material. Previously accepted papers (including ones accepted to the ICML main conference) are allowed and can be submitted in their original format. Outstanding papers will be selected for short oral presentations, while all accepted papers will be presented as posters. At least one author from each accepted paper is expected to attend the workshop to present their paper in person.

Notification of acceptance: Monday, June 19, 2023



Invited Speakers

Geoffrey Hinton

University of Toronto

Irina Rish

Université de Montréal

Edouard Oyallon

CNRS / Sorbonne

Claudia Clopath

Imperial College of London

Timoleon Moraitis

 Huawei Technologies
Zurich Research Center

Qu Yang

National University of Singapore

Stephen Gou





David I. Inouye

Purdue University

Mengye Ren

New York University

Mateusz Malinowski


Michael Eickenberg

Flatiron Institute

Gao Huang

Tsinghua University

Eugene Belilovsky

Mila / Concordia University



Schedule (tentative)
Saturday, July 29th

The most up-to-date schedule can be found on the LLW workshop page on the ICML 2023 conference website


We hope to see you @ ICML 2023 in Hawaii!