For separable multi-output GPs, oracle prediction gain and cross-dependence estimability are controlled by heterotopic design geometry, so interleaved and separated zero-overlap designs are not statistically equivalent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
When is multivariate kriging worthwhile? A design-geometry analysis of heterotopic multi-output Gaussian processes
For separable multi-output GPs, oracle prediction gain and cross-dependence estimability are controlled by heterotopic design geometry, so interleaved and separated zero-overlap designs are not statistically equivalent.