Deep neural networks are lazy : on the inductive bias of deep learning

Deep learning models exhibit superior generalization performance despite being heavily overparametrized. Although widely observed in practice, there is currently very little theoretical backing for such a phenomena. In this thesis, we propose a step forward towards understanding generalization in deep learning. We present evidence that deep neural networks have an inherent inductive bias that makes them inclined to learn generalizable hypotheses and avoid memorization. In this respect, we propose results that suggest that the inductive bias stems from neural networks being lazy: they tend to learn simpler rules first. We also propose a definition of simplicity in deep learning based on the implicit priors ingrained in deep neural networks.

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

2019

Author dc:creator

• Mansour, Tarek,M. Eng.Massachusetts Institute of Technology.

Advisor dc:contributor.advisor

• Aleksander Madry.

• Electrical Engineering and Computer Science.

Statement dc:rights

• MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/121680

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/121680