ezyrb.approximation.gpr.GPR.optimal_mu

GPR.optimal_mu(bounds, optimization_restart=10)[source]

Proposes the next sampling point by looking at the point where the Gaussian covariance is maximized. A gradient method (with multi starting points) is adopted for the optimization.

Parameters:

  • bounds (numpy.ndarray) – the boundaries in the gradient optimization. The shape must be (input_dim, 2), where input_dim is the dimension of the input points.

  • optimization_restart (int) – the number of restart in the gradient optimization. Default is 10.