How early can we average Neural Networks?

There is a recurring observation in deep learning that neural networks can be combined simply with arithmetic averages over their parameters. This observation has led to many new research directions in model ensembling, meta-learning, federated learning, and optimization. We investigate the evolution of this phenomenon during the training trajectory of neural network models initialized from a common set of parameters (parent). Surprisingly, the benefit of averaging the parameters persists over long child trajectories from parent parameters with minimal training. Furthermore, we find that the parent can be merged with a single child with significant improvement in both training and test loss. Through analysis of the loss landscape, we find that the loss becomes sufficiently convex early on in training, and, as a consequence, models obtained by averaging multiple children often outperform any individual child.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2023

Author dc:creator

• Nasimov, Umarbek

Advisor dc:contributor.advisor

• Poggio, Tomaso

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright retained by author(s)

Licence dc:rights.uri

• https://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/151660

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/151660