We wish for this workshop to serve as a platform to foster discussion and scientific consensus about the implications of overparameterization. As it is has been of relevance to machine learning practice for the past several years, we think a workshop with a specific focus on overparameterization is timely for the community. We hope this will lead to a more unified view, identification of new questions, and collaborations.

We invite contributions on a range of topics, including, but not limited to:

• Studies of benign overfitting

• Multiple descent risk curves

• Overparameterized models beyond neural networks

• Effects of model compression

• Memorization in overparametrized models

• Conditions under which overparameterization hurts generalization

• Optimization methods tailored for overparametrized models

• Robustness of overparametrized models

• Implicit bias/regularization of training methods for overparameterized models

• Interplay between data and overparameterization

• Empirical studies of the impact of overparameterization

Accepted papers will present their work in a poster format and top submissions will be given a spotlight presentation.

Submission Instructions

Please submit your anonymized paper through CMT.

The main part of a submission should be at most 4 pages long. There is no space limit for references, acknowledgements, and details included in appendices. Please upload a single PDF that includes the main paper and any supplementary material.

Papers should be formatted with at least a 10 pt font, standard line spacing, and a 1 inch margin. Please use our modified ICML 2021 style file which can be downloaded here.

We welcome all unpublished results and also papers that were published in 2020 or later.

Please direct any questions to the organizers at icml2021.oppo@gmail.com.

Important Dates

• Submission Deadline: June 6, 2021 AOE (EXTENDED)

• Notification: June 26, 2021

• Workshop: ICML 2021 July 23 or July 24, 2021