pybop.optimisers._simulated_annealing

Classes

SimulatedAnnealingImpl

Simulated Annealing optimiser, implementing the classic temperature-based

Module Contents

class pybop.optimisers._simulated_annealing.SimulatedAnnealingImpl(x0: numpy.ndarray, sigma0: list[float] | None, boundaries: pints.Boundaries | None)

Bases: pints.Optimiser

Simulated Annealing optimiser, implementing the classic temperature-based probabilistic optimisation method.

This method uses a temperature schedule to control the probability of accepting worse solutions as it explores the parameter space. As the temperature decreases, the algorithm becomes more selective, eventually converging to a local or global optimum.

The probability of accepting a worse solution is given by:

.. math::

P(accept) = exp(-(f_{ ext{new}} - fold)/T)

The temperature decreases according to the cooling schedule:

.. math::

T = T0 * lpha^k

where: - :math: T0 is the initial temperature - :math: lpha is the cooling rate (between 0 and 1) - :math: k is the iteration number

Parameters:

• x0 (numpy array) – Initial position

• sigma0 (float) – Initial step size

• boundaries (dict, optional) – Optional boundaries for parameters

ask()

Returns a list of next points in the parameter-space to evaluate from the optimiser.

f_best()

Returns the best score found.

n_hyper_parameters()

Returns the number of hyper-parameters for this optimiser.

name()

Returns the name of this optimiser.

needs_sensitivities()

Returns whether this method needs sensitivities.

running()

Returns whether the optimisation is still running.

tell(reply)

Receives a list of function values from the cost function from points previously specified by self.ask(), and updates the optimiser state accordingly.

x_best()

Returns the best position found.

_current

_current_f

_f_best

_iterations = 0

_proposed

_ready_for_tell = False

_running = False

_temperature = 1.0

_temperature_decay = 0.95

_x_best

property cooling_rate

property temperature