Provable Data Subset Selection For Efficient Neural Networks Training

Murad Tukan, Samson Zhou, Alaa Maalouf, Daniela Rus, Vladimir Braverman, Dan Feldman

Research output: Contribution to journalConference articlepeer-review

Abstract

Radial basis function neural networks (RBFNN) are well-known for their capability to approximate any continuous function on a closed bounded set with arbitrary precision given enough hidden neurons. In this paper, we introduce the first algorithm to construct coresets for RBFNNs, i.e., small weighted subsets that approximate the loss of the input data on any radial basis function network and thus approximate any function defined by an RBFNN on the larger input data. In particular, we construct coresets for radial basis and Laplacian loss functions. We then use our coresets to obtain a provable data subset selection algorithm for training deep neural networks. Since our coresets approximate every function, they also approximate the gradient of each weight in a neural network, which is a particular function on the input. We then perform empirical evaluations on function approximation and dataset subset selection on popular network architectures and data sets, demonstrating the efficacy and accuracy of our coreset construction.

Original languageEnglish
Pages (from-to)34533-34555
Number of pages23
JournalProceedings of Machine Learning Research
Volume202
StatePublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023

Bibliographical note

Publisher Copyright:
© 2023 Proceedings of Machine Learning Research. All rights reserved.

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Provable Data Subset Selection For Efficient Neural Networks Training'. Together they form a unique fingerprint.

Cite this