Early Stopping for Time-series Applications

Contact: Mahsa Forouzesh

Project Description:

For time-series applications, cross-validation is not valid because random-shuffling over the data gives imbalanced subsets that might be dependent on each other. In this project, we would like to explore possible replacements for cross-validation in such settings. In particular, we would like to study the potential benefits of gradient disparity (introduced in [1]) as an early stopping criterion that does not require a held-out validation set.

[1] Forouzesh and Thiran, Disparity Between Batches as a Signal for Early Stopping, ECML/PKDD 2021

Required Skills:

  • Solid knowledge in machine learning
  • Strong Python programming skills
  • (preferred) Experience with ML libraries such as Pytorch or Tensorflow

To apply please send your CV and transcript to Mahsa Forouzesh