vkoga

pymor-demo vkoga [ARGS]

Approximates a function with 2d output from training data using VKOGA.

Parameters:

TRAINING-POINTS-SAMPLING, --training-points-sampling

Method for sampling the training points. [Choices: random, uniform, Default: random]

KERNEL, --kernel

Kernel to use in VKOGA. [Choices: Gaussian, Matern, RationalQuadratic, Default: Gaussian]

NUM-TRAINING-POINTS, --num-training-points

Number of training points in the weak greedy algorithm. [Default: 40]

GREEDY-CRITERION, --greedy-criterion

Selection criterion for the greedy algorithm. [Choices: fp, f, p, Default: fp]

MAX-CENTERS, --max-centers

Maximum number of selected centers in the greedy algorithm. [Default: 20]

TOL, --tol

Tolerance for the weak greedy algorithm. [Default: 1e-06]

REG, --reg

Regularization parameter for the kernel interpolation. [Default: 1e-12]

LENGTH-SCALE, --length-scale

The length scale parameter of the kernel. Only used when kernel = diagonal. [Default: 1.0]

TEST-EXTEND, --test-extend, --no-test-extend

If True, also test the incremental extend method by fitting on 1/2 of the data and extending twice with 1/4 each, then comparing with the full fit. [Default: True]