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

Modern computer systems are highly configurable, with hundreds ofconfiguration options that interact, resulting in an enormous configurationspace. As a result, optimizing performance goals (e.g., latency) in suchsystems is challenging due to frequent uncertainties in their environments(e.g., workload fluctuations). Recently, transfer learning has been applied toaddress this problem by reusing knowledge from configuration measurements fromthe source environments, where it is cheaper to intervene than the targetenvironment, where any intervention is costly or impossible. Recent empiricalresearch showed that statistical models can perform poorly when the deploymentenvironment changes because the behavior of certain variables in the models canchange dramatically from source to target. To address this issue, we proposeCAMEO, a method that identifies invariant causal predictors under environmentalchanges, allowing the optimization process to operate in a reduced searchspace, leading to faster optimization of system performance. We demonstratesignificant performance improvements over state-of-the-art optimization methodsin MLperf deep learning systems, a video analytics pipeline, and a databasesystem.

CAMEO: A Causal Transfer Learning Approach for Performance Optimization of Configurable Computer Systems