paper-with-me

홈 › Papers

Early Stopping is Nonparametric Variational Inference

2015-04-06 · Dougal Maclaurin, David Duvenaud, Ryan P. Adams

We show that unconverged stochastic gradient descent can be interpreted as a procedure that samples from a nonparametric variational approximate posterior distribution. This distribution is implicitly defined as the transformation of an initial distribution by a sequence of optimization updates. By tracking the change in entropy over this sequence of transformations during optimization, we form a scalable, unbiased estimate of the variational lower bound on the log marginal likelihood. We can use this bound to optimize hyperparameters instead of using cross-validation. This Bayesian interpretation of SGD suggests improved, overfitting-resistant optimization procedures, and gives a theoretical foundation for popular tricks such as early stopping and ensembling. We investigate the properties of this marginal likelihood estimator on neural network models.

📄 PDF Abstract BibTeX arXiv:1504.01344

Code (1)

HIPS/maxwells-daemon 공식 구현

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Variational Laplace for Bayesian neural networks

2020-11-20 · Ali Unlu, Laurence Aitchison

We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-netwo…

BenchmarkingVariational Inference

Variational Laplace for Bayesian neural networks

2021-02-27 · Ali Unlu, Laurence Aitchison

We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-netwo…

BenchmarkingImage ClassificationVariational Inference

Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression

2024-11-05 · Yingzhen Yang, Ping Li

We study nonparametric regression by an over-parameterized two-layer neural network trained by gradient descent (GD) in this paper. We show that, if the neural network is trained by GD with early stopping, then the train…

regression

Early stopping and polynomial smoothing in regression with reproducing kernels

2020-07-14 · Yaroslav Averyanov, Alain Celisse

In this paper, we study the problem of early stopping for iterative learning algorithms in a reproducing kernel Hilbert space (RKHS) in the nonparametric regression framework. In particular, we work with the gradient des…

regression

Early Stopping for Nonparametric Testing

2018-05-25 · NeurIPS 2018 12 · Meimei Liu, Guang Cheng

Early stopping of iterative algorithms is an algorithmic regularization method to avoid over-fitting in estimation and classification. In this paper, we show that early stopping can also be applied to obtain the minimax …

General Classification