intrinsicDimension (version 1.2.0)

essReference: ESS Reference Values

Description

Reference values for the ESS dimension estimation method

Usage

essReference(ver, d, maxdim, mindim=1)

Arguments

ver

Possible values: 'a' and 'b'. See Johnsson et al. (2015).

d

For ver = 'a', any value of d is possible, for ver = 'b', only d = 1 is supported.

maxdim

The largest dimension for which reference values should be computed.

mindim

The smallest dimension for which reference values should be computed.

Value

A vector of length maxdim-(mindim-1), where each slot represents the reference value.

Details

The ESS reference values are used by the ESS algorithm (essLocalDimEst) to compute the final dimension estimate.

References

Johnsson, K., Soneson, C., & Fontes, M. (2015). Low Bias Local Intrinsic Dimension Estimation from Expected Simplex Skewness. IEEE Trans. Pattern Anal. Mach. Intell., 37(1), 196-202.

Examples

# NOT RUN {
essReference('a', 3, maxdim=500)
essReference('b', 1, maxdim=30, mindim=3)
# }