torch_openreml.covariance.simple_param_specs¶

torch_openreml.covariance.simple_param_specs(n, default=0.0, trans=None)[source]¶

Create a parameter specification dictionary with n parameters.

Each parameter is named "theta_0", "theta_1", …, is not fixed, and uses a common transform for all parameters. An optional scalar default value can be provided.

Parameters:

n (int) – Number of parameters to create.
default (float or torch.Tensor, optional) – Default value for each parameter. If a tensor, it must be 1D with shape (1,). Defaults to 0.0.
trans (Transform, optional) – Transform to apply to all parameters. Defaults to TransformIdentity (unconstrained).

Returns:

A dictionary mapping parameter names to specification dicts of the form {"fixed": False, "default": tensor, "trans": trans}.

Return type:

dict

Raises:

ValueError – If default is a tensor without shape (1,).
TypeError – If default is not a float, int, or 1D tensor.

Example:

from torch_openreml.covariance.param import simple_param_specs

simple_param_specs(3)

{'theta_0': {'fixed': False,
  'default': tensor([0.]),
  'trans': TransformIdentity()},
 'theta_1': {'fixed': False,
  'default': tensor([0.]),
  'trans': TransformIdentity()},
 'theta_2': {'fixed': False,
  'default': tensor([0.]),
  'trans': TransformIdentity()}}