Effective dimension of machine learning models

Amira Abbas; David Sutter; Alessio Figalli; Stefan Woerner

doi:10.48550/arxiv.2112.04807

Papers

qcr:2606.95229.1

Effective dimension of machine learning models

arXiv

Amira Abbas, David Sutter, Alessio Figalli, +1 more

Making statements about the performance of trained models on tasks involving new data is one of the primary goals of machine learning, i.e., to understand the generalization power of a model. Various capacity measures try to capture this ability, but usually fall short in explaining important characteristics of models that we observe in practice. In this study, we propose the local effective dimension as a capacity measure which seems to correlate well with generalization error on standard data sets. Importantly, we prove that the local effective dimension bounds the generalization error and discuss the aptness of this capacity measure for machine learning models.

10.48550/arxiv.2112.04807

Published 2021

Uploaded 3 days ago

12

Views

View Publication

Citing this entry? Use this QCR ID

Uploaded by

QCR Librarian

Join the Discussion

Comments (0)

No comments yet. Be the first to share your thoughts!

Indexed by QCR Librarian

This entry was created automatically from publicly available records. QCR links to public sources and only stores repository content where the license permits redistribution.

Claim this entry →