InitialDesign

class probnum.quad.solvers.initial_designs.InitialDesign(n_nodes, measure)

Bases: ABC

An abstract class for an initial design for Bayesian quadrature.

Parameters:

  • n_nodes (IntLike) – The number of nodes to be designed.

  • measure (IntegrationMeasure) – The integration measure.

Attributes Summary

requires_rng

Whether the initial design requires a random number generator when called.

Methods Summary

__call__(rng)

Get the initial nodes.

Attributes Documentation

requires_rng

Whether the initial design requires a random number generator when called.

Methods Documentation

abstract __call__(rng)[source]

Get the initial nodes.

Parameters:

rng (Generator | None) – A random number generator.

Returns:

shape=(n_nodes, input_dim) – Initial design nodes.

Return type:

nodes