paper-with-me

Papers

Optimizing for Generalization in Machine Learning with Cross-Validation Gradients

2019-05-01 · ICLR 2019 5 · Barratt, Shane, Sharma, Rishi

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 propose a cross-validation gradient method (CVGM) for hyperparameter optimization. Our method enables efficient optimization in high-dimensional hyperparameter spaces of the cross-validation risk, the best surrogate of the true generalization ability of our learning algorithm.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningHyperparameter Optimizationregression

Similar Papers 제목 키워드 기반

Optimizing for Generalization in Machine Learning with Cross-Validation Gradients

2018-05-18 · Shane Barratt, Rishi Sharma

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 th…

BIG-bench Machine LearningHyperparameter Optimizationregression

The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial

2019-05-28 · Benyamin Ghojogh, Mark Crowley

In this tutorial paper, we first define mean squared error, variance, covariance, and bias of both random variables and classification/predictor models. Then, we formulate the true and generalization errors of the model …

L2 Regularization

Deep Bilevel Learning

2018-09-05 · ECCV 2018 9 · Simon Jenni, Paolo Favaro

We present a novel regularization approach to train neural networks that enjoys better generalization and test error than standard stochastic gradient descent. Our approach is based on the principles of cross-validation,…

Bilevel Optimization

Early Stopping without a Validation Set

2017-03-28 · Maren Mahsereci, Lukas Balles, Christoph Lassner, Philipp Hennig

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 pr…

regression

Information-Theoretic Generalization Bounds for Stochastic Gradient Descent

2021-02-01 · Gergely Neu, Gintare Karolina Dziugaite, Mahdi Haghifam, Daniel M. Roy

We study the generalization properties of the popular stochastic optimization method known as stochastic gradient descent (SGD) for optimizing general non-convex loss functions. Our main contribution is providing upper b…

Generalization BoundsStochastic Optimization