Optimizing for Generalization in Machine Learning with Cross-Validation Gradients

@article{Barratt2018OptimizingFG,
  title={Optimizing for Generalization in Machine Learning with Cross-Validation Gradients},
  author={Shane T. Barratt and Rishi Sharma},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.07072}
}
Cross-validation is the workhorse of modern applied statistics and machine learning, as it provides a principled framework for selecting the model that maximizes generalization performance. In this paper, we show that the cross-validation risk is differentiable with respect to the hyperparameters and training data for many common machine learning algorithms, including logistic regression, elastic-net regression, and support vector machines. Leveraging this property of differentiability, we… CONTINUE READING
9
Twitter Mentions