English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Effective regularization techniques are highly desired in deep learning foralleviating overfitting and improving generalization. This work proposes a newregularization scheme, based on the understanding that the flat local minima ofthe empirical risk cause the model to generalize better. This scheme isreferred to as adversarial model perturbation (AMP), where instead of directlyminimizing the empirical risk, an alternative "AMP loss" is minimized via SGD.Specifically, the AMP loss is obtained from the empirical risk by applying the"worst" norm-bounded perturbation on each point in the parameter space.Comparing with most existing regularization schemes, AMP has strong theoreticaljustifications, in that minimizing the AMP loss can be shown theoretically tofavour flat local minima of the empirical risk. Extensive experiments onvarious modern deep architectures establish AMP as a new state of the art amongregularization schemes. Our code is available athttps://github.com/hiyouga/AMP-Regularizer.

Regularizing Neural Networks via Adversarial Model Perturbation