transport.samples.kernels.streaming_sqeuclid.shifted_to_standard_potentials
def shifted_to_standard_potentials(f_hat: torch.Tensor, g_hat: torch.Tensor, alpha: torch.Tensor, beta: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]Convert shifted potentials back to standard form.
Args:
f_hat: Shifted source potential [n]
g_hat: Shifted target potential [m]
alpha: Source squared norms [n] = cost_scale * ||x||²
beta: Target squared norms [m] = cost_scale * ||y||²
Returns:
f: Standard source potential [n] = f_hat + alpha
g: Standard target potential [m] = g_hat + beta
Source: torchmatch/transport/samples/kernels/streaming_sqeuclid.py:1511