squlearn.qnn.loss.VarianceLoss

class squlearn.qnn.loss.VarianceLoss(alpha: float | Callable[[int], float] = 0.005)

Variance loss for regression.

Parameters:

alpha (float, Callable[[int], float]) – Weight value \(\alpha\)

gradient(value_dict: dict, **kwargs) → ndarray | tuple[ndarray, ndarray]

Returns the gradient of the variance.

This function calculates the gradient of the variance values in value_dict.

Parameters:

• value_dict (dict) – Contains calculated values of the model

• iteration (int) – iteration number, if variance_factor is a function

• multiple_output (bool) – True if the QNN has multiple outputs

Returns:

Gradient values

set_opt_param_op(opt_param_op: bool = True)

Sets the opt_param_op flag.

Parameters:

opt_param_op (bool) – True, if operator has trainable parameters

value(value_dict: dict, **kwargs) → float

Returns the variance.

This function returns the weighted variance as

\[L_\operatorname{Var} = \alpha \sum_i \operatorname{Var}_i\]

Parameters:

• value_dict (dict) – Contains calculated values of the model

• iteration (int) – iteration number, if alpha is a callable function

Returns:

Loss value

variance(value_dict: dict, **kwargs) → float

Returns 0 since we neglect the variance of the variance.