acv_multifidelity

Approximate control variate (ACV) algorithm that mimics MFMC by employing a nested pyramid sample pattern

This ACV variant uses sample set definitions that are similar to multifidelity Monte Carlo (MFMC), in that sample sets are nested with each new level adding an increment on top of the previous.

Specification

  • Alias: acv_mf

  • Arguments: None

Description

Theory

Refer to [GGEJ20] for a helpful sample set diagram.