function

transport.samples.kernels.streaming_sqeuclid.compute_bias_f

def compute_bias_f(g: torch.Tensor, beta: torch.Tensor, delta: torch.Tensor, eps: float) -> torch.Tensor

Compute pre-scaled bias for f-update: u = (ĝ + δ)/ε.

Args: g: Current g potential [m] beta: Target squared norms [m] = cost_scale * ||y||² delta: Scaled log target weights [m] = eps * log(b) eps: Regularization parameter Returns: u: Pre-scaled bias [m] = (g - beta + delta) / eps

Source: torchmatch/transport/samples/kernels/streaming_sqeuclid.py:109