Statistical mechanics approach to early stopping and weight decay

1998 ◽  
Vol 58 (1) ◽  
pp. 833-844 ◽  
Author(s):  
Siegfried Bös
2009 ◽  
Vol 36 (10) ◽  
pp. 4810-4818 ◽  
Author(s):  
Richard M. Zur ◽  
Yulei Jiang ◽  
Lorenzo L. Pesce ◽  
Karen Drukker

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1629
Author(s):  
Ali Unlu ◽  
Laurence Aitchison

We developed 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-network weights. The Variational Laplace objective is simple to evaluate, as it is the log-likelihood plus weight-decay, plus a squared-gradient regularizer. Variational Laplace gave better test performance and expected calibration errors than maximum a posteriori inference and standard sampling-based variational inference, despite using the same variational approximate posterior. Finally, we emphasize the care needed in benchmarking standard VI, as there is a risk of stopping before the variance parameters have converged. We show that early-stopping can be avoided by increasing the learning rate for the variance parameters.


1992 ◽  
Vol 2 (5) ◽  
pp. 1215-1236 ◽  
Author(s):  
Jonathan V. Selinger ◽  
Robijn F. Bruinsma

Sign in / Sign up

Export Citation Format

Share Document