Header logo is ps

Early Stopping Without a Validation Set





Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization. To find a good point to halt the optimizer, a common practice is to split the dataset into a training and a smaller validation set to obtain an ongoing estimate of the generalization performance. In this paper we propose a novel early stopping criterion which is based on fast-to-compute, local statistics of the computed gradients and entirely removes the need for a held-out validation set. Our experiments show that this is a viable approach in the setting of least-squares and logistic regression as well as neural networks.

Author(s): Maren Mahsereci and Lukas Balles and Christoph Lassner and Philipp Hennig
Journal: arXiv preprint arXiv:1703.09580
Year: 2017

Department(s): Perceiving Systems, Probabilistic Numerics
Research Project(s): Efficient and Scalable Inference
Probabilistic Methods for Nonlinear Optimization
Bibtex Type: Article (article)
Paper Type: Journal

URL: https://arxiv.org/abs/1703.09580


  title = {Early Stopping Without a Validation Set},
  author = {Mahsereci, Maren and Balles, Lukas and Lassner, Christoph and Hennig, Philipp},
  journal = {arXiv preprint arXiv:1703.09580},
  year = {2017},
  url = {https://arxiv.org/abs/1703.09580}