assignment.SoftAssignment.__init__
def __init__(self, *args = (), epsilon: float = DEFAULT_EPSILON, num_iter: int = DEFAULT_NUM_ITER, **kwargs = {})Initialize the soft-assignment module.
Parameters
| Name | Type | Description |
|---|---|---|
| epsilon = DEFAULT_EPSILON | float | Entropy-regularization weight. Smaller values yield sharper, more discrete transport plans at the cost of slower Sinkhorn convergence and reduced numerical stability. |
| num_iter = DEFAULT_NUM_ITER | int | Number of Sinkhorn iterations. |
| *args = () | Positional arguments passed to :class:`.Assignment`. | |
| **kwargs = {} | Keyword arguments passed to :class:`.Assignment`. |
Source: unitrack/assignment/_soft.py:43