pyriemann_qiskit.utils.hyper_params_factory.get_spsa

pyriemann_qiskit.utils.hyper_params_factory.get_spsa(max_trials=40, c=(None, None, None, None, 4.0))[source]

Return an instance of SPSA.

SPSA [1], [2] is an algorithmic method for optimizing systems with multiple unknown parameters. For more details, see [3] and [4].

Parameters:

  • max_trials (int (default:40)) – Maximum number of iterations to perform.

  • c (tuple[float | None] (default:(None, None, None, None, 4.0))) – The 5 control parameters for SPSA algorithms, namely: the initial point, the initial perturbation, alpha, gamma and the stability constant. See [3] for implementation details. This function set the default value of the control parameters for the calibrate method of the implementation.

Returns:

ret – An instance of SPSA.

Return type:

SPSA

References

[1]

Spall, J. C. (2012), “Stochastic Optimization,” in Handbook of Computational Statistics: Concepts and Methods (2nd ed.) (J. Gentle, W. Härdle, and Y. Mori, eds.), Springer−Verlag, Heidelberg, Chapter 7, pp. 173–201. dx.doi.org/10.1007/978-3-642-21551-3_7

[2]

Spall, J. C. (1999), “Stochastic Optimization: Stochastic Approximation and Simulated Annealing,” in Encyclopedia of Electrical and Electronics Engineering (J. G. Webster, ed.), Wiley, New York, vol. 20, pp. 529–542