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

Natural gradient methods have been used to optimise the parameters ofprobability distributions in a variety of settings, often resulting infast-converging procedures. Unfortunately, for many distributions of interest,computing the natural gradient has a number of challenges. In this work wepropose a novel technique for tackling such issues, which involves reframingthe optimisation as one with respect to the parameters of a surrogatedistribution, for which computing the natural gradient is easy. We give severalexamples of existing methods that can be interpreted as applying thistechnique, and propose a new method for applying it to a wide variety ofproblems. Our method expands the set of distributions that can be efficientlytargeted with natural gradients. Furthermore, it is fast, easy to understand,simple to implement using standard autodiff software, and does not requirelengthy model-specific derivations. We demonstrate our method on maximumlikelihood estimation and variational inference tasks.

Optimising Distributions with Natural Gradient Surrogates