アイテム詳細

登録内容を編集

このアイテムは取り下げられました。詳細要約

取り下げ

学術論文

Pruning from Adaptive Regularization

MPS-Authors

/persons/resource/persons84156

Rasmussen, CE
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

公開されているフルテキストはありません

付随資料 (公開)

There is no public supplementary material available

引用

Hansen, L., & Rasmussen, C. (1994). Pruning from Adaptive Regularization. Neural Computation, 6(6), 1222-1231.

要旨

Inspired by the recent upsurge of interest in Bayesian methods we consider adaptive regularization. A generalization based scheme for adaptation of regularization parameters is introduced and compared to Bayesian regularization.We show that pruning arises naturally within both adaptive regularization schemes. As model example we have chosen the simplest possible: estimating the mean of a random variable with known variance. Marked similarities are found between the two methods in that they both involve a "noise limit", below which they regularize with infinite weight decay, i.e., they prune.However, pruning is not always beneficial. We show explicitly that both methods in some cases may increase the generalization error. This corresponds to situations where the underlying assumptions of the regularizer are poorly matched to the environment.