Sparsity in Neural Networks

Advancing Understanding and Practice

Recordings are now available!

Day-1 Day-2

Slides are available at schedule-page.

July 8-9th 2021, 2pm-7pm GMT, Virtual

Call for Papers/Abstract

A neural network is sparse when a portion of its parameters have been fixed to 0. Neural network sparsity is:
  • A compelling practical opportunity to reduce the cost of training and inference (through applied work on algorithms, systems, and hardware);
  • An important topic for understanding how neural networks train with/without overparameterization and the representations they learn (through theoretical and scientific work).

Research interest in sparsity in deep learning have exploded in recent years from both the academic and the industry, and we believe the community is now large and diverse enough to join together to discuss shared research priorities and cross-cutting issues. Currently, the communities working on aspects of sparsity and related problems are disparate, oftentimes presenting at separate venues for separate audiences.
This workshop aims to bring together researchers working on problems related to the practical, theoretical, and scientific aspects of neural network sparsity, and members of adjacent communities, in order to build connections across different areas, create opportunities for new collaborations, and articulate shared challenges.
We believe the time is right to bring these stakeholders together, and we intend this workshop as the way to do so. We aspire to build a lasting, interdisciplinary research community among those who share an interest in neural network sparsity.

Our Speakers

Anna Golubeva

IAIFI, Boston

Diana Marculescu

UT Austin

Cliff Young


Gintare Karolina Dziugaite


Sara Hooker


Selima Curci


Paulius Micikevicius


Rosanne Liu

Google/ML Collective

Torsten Hoefler

ETH Zürich

Friedemann Zenke

FMI, Basel

Natalia Vassilieva

Cerebras Systems

Mitchell Wortsman

University of Washington