sparse_ho.optimizers.LineSearch

class sparse_ho.optimizers.LineSearch(n_outer=100, verbose=False, tolerance_decrease='constant', tol=1e-05, t_max=10000)

Gradient descent with line search for the outer problem.

The code is taken from here: https://github.com/fabianp/hoag/blob/master/hoag/hoag.py

Parameters

n_outer: int, optional (default=100).

number of maximum updates of alpha.

verbose: bool, optional (default=False)

Verbosity.

tolerance_decrease: string, optional (default=”constant”)

Tolerance decrease strategy for approximate gradient.

tolfloat, optional (default=1e-5)

Tolerance for the inner optimization solver.

t_max: float, optional (default=10000)

Maximum running time threshold in seconds.

__init__(n_outer=100, verbose=False, tolerance_decrease='constant', tol=1e-05, t_max=10000)

Methods

__init__([n_outer, verbose, ...])