English

Robust and Active Learning for Deep Neural Network Regression

Machine Learning 2021-07-29 v1

Abstract

We describe a gradient-based method to discover local error maximizers of a deep neural network (DNN) used for regression, assuming the availability of an "oracle" capable of providing real-valued supervision (a regression target) for samples. For example, the oracle could be a numerical solver which, operationally, is much slower than the DNN. Given a discovered set of local error maximizers, the DNN is either fine-tuned or retrained in the manner of active learning.

Keywords

Cite

@article{arxiv.2107.13124,
  title  = {Robust and Active Learning for Deep Neural Network Regression},
  author = {Xi Li and George Kesidis and David J. Miller and Maxime Bergeron and Ryan Ferguson and Vladimir Lucic},
  journal= {arXiv preprint arXiv:2107.13124},
  year   = {2021}
}
R2 v1 2026-06-24T04:34:55.149Z