Skip to main content
IBM Quantum Platform
Esta página pertenece a una versión antigua de Qiskit SDK y no existe en la versión más reciente. Te recomendamos que actualices a la última versión. Consulta las notas de la versión para obtener más información.

GradientDescentState

class qiskit.algorithms.optimizers.GradientDescentState(x, fun, jac, nfev, njev, nit, stepsize, learning_rate)

GitHub

Bases: OptimizerState

State of GradientDescent.

Dataclass with all the information of an optimizer plus the learning_rate and the stepsize.


Attributes

stepsize

Tipo: float | None

Norm of the gradient on the last step.

learning_rate

Tipo: LearningRate

Learning rate at the current step of the optimization process.

It behaves like a generator, (use next(learning_rate) to get the learning rate for the next step) but it can also return the current learning rate with learning_rate.current.

x

Tipo: POINT

Current optimization parameters.

fun

Tipo: Callable[[POINT], float] | None

Function being optimized.

jac

Tipo: Callable[[POINT], POINT] | None

Jacobian of the function being optimized.

nfev

Tipo: int | None

Number of function evaluations so far in the optimization.

njev

Tipo: int | None

Number of jacobian evaluations so far in the opimization.

nit

Tipo: int | None

Number of optimization steps performed so far in the optimization.

¿Le ha resultado útil esta página?
Informe de un error, de una errata o solicite contenido en GitHub.