function covariances

deeptime.decomposition.deep.covariances(x: Tensor, y: Tensor, remove_mean: bool = True)

Computes instantaneous and time-lagged covariances matrices.

Parameters:
  • x ((T, n) torch.Tensor) – Instantaneous data.

  • y ((T, n) torch.Tensor) – Time-lagged data.

  • remove_mean (bool, default=True) – Whether to remove the mean of x and y.

Returns:

  • cov_00 ((n, n) torch.Tensor) – Auto-covariance matrix of x.

  • cov_0t ((n, n) torch.Tensor) – Cross-covariance matrix of x and y.

  • cov_tt ((n, n) torch.Tensor) – Auto-covariance matrix of y.

See also

deeptime.covariance.Covariance

Estimator yielding these kind of covariance matrices based on raw numpy arrays using an online estimation procedure.