AdaptiveInducedPCE

class pyapprox.surrogates.AdaptiveInducedPCE(num_vars, cond_tol=100.0, induced_sampling=True, fit_opts={'omp_tol': 0, 'precond_func': <function christoffel_preconditioning_function>})

Bases: SubSpaceRefinementManager

An adaptive PCE built using induced sampling and generalized sparse grid like refinement.

Methods Summary

__call__(samples[, return_grad])	Call self as a function.
add_new_subspaces(new_subspace_indices)
allocate_initial_samples()
build([callback])
create_new_subspaces_data(new_subspace_indices)
fit()
get_active_unique_poly_indices()
increment_samples(current_poly_indices, ...)
num_training_samples()
set_function(function[, var_trans, pce])
set_polynomial_chaos_expansion([pce])
set_preconditioning_function(precond_func)	precond_func : callable

Methods Documentation

__call__(samples, return_grad=False)

Call self as a function.

add_new_subspaces(new_subspace_indices)

allocate_initial_samples()

build(callback=None)

create_new_subspaces_data(new_subspace_indices)

fit()

get_active_unique_poly_indices()

increment_samples(current_poly_indices, unique_poly_indices)

num_training_samples()

set_function(function, var_trans=None, pce=None)

set_polynomial_chaos_expansion(pce=None)

set_preconditioning_function(precond_func)

precond_funccallable

Callable function with signature precond_func(basis_matrix,samples)