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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Learning neural ODEs often requires solving very stiff ODE systems, primarilyusing explicit adaptive step size ODE solvers. These solvers arecomputationally expensive, requiring the use of tiny step sizes for numericalstability and accuracy guarantees. This paper considers learning neural ODEsusing implicit ODE solvers of different orders leveraging proximal operators.The proximal implicit solver consists of inner-outer iterations: the inneriterations approximate each implicit update step using a fast optimizationalgorithm, and the outer iterations solve the ODE system over time. Theproximal implicit ODE solver guarantees superiority over explicit solvers innumerical stability and computational efficiency. We validate the advantages ofproximal implicit solvers over existing popular neural ODE solvers on variouschallenging benchmark tasks, including learning continuous-depth graph neuralnetworks and continuous normalizing flows.

Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs