pyriemann.geometry.mean.mean_bmp

pyriemann.geometry.mean.mean_bmp(X, *, tol=1e-07, maxiter=50, sample_weight=None)

Bini-Meini-Poloni (BMP) mean of SPD/HPD matrices.

Bini-Meini-Poloni (BMP) mean is computed recursively [1].

Parameters:

Xndarray, shape (…, n_matrices, n, n)

Set of SPD/HPD matrices.

tolfloat, default=1e-7

Tolerance to stop the gradient descent.

maxiterint, default=50

Maximum number of iterations.

sample_weightNone | ndarray, shape (n_matrices,), default=None

Weights for each matrix. If None, it uses equal weights.

Returns:

Mndarray, shape (n, n)

BMP mean.

See also

gmean

Notes

Added in version 0.12.

References

[1]

An effective matrix geometric mean satisfying the Ando–Li–Mathias properties D. Bini, B. Meini and F. Poloni. Mathematics of Computation. 2010