Module `laplace.curvature.asdfghjkl`

Classes

class AsdfghjklInterface (model, likelihood, last_layer=False, subnetwork_indices=None)

Interface for asdfghjkl backend.

def jacobians(self, x, enable_backprop=False)

Compute Jacobians $\nabla_\theta f(x;\theta)$ at current parameter $\theta$ using asdfghjkl's gradient per output dimension.

x : torch.Tensor: input data (batch, input_shape) on compatible device with model.
enable_backprop : bool, default = False: whether to enable backprop through the Js and f w.r.t. x

def gradients(self, x, y)

Compute gradients $\nabla_\theta \ell(f(x;\theta, y)$ at current parameter $\theta$ using asdfghjkl's backend.

x : torch.Tensor: input data (batch, input_shape) on compatible device with model.
y : torch.Tensor

class AsdfghjklHessian (model, likelihood, last_layer=False, low_rank=10)

Interface for asdfghjkl backend.

class AsdfghjklGGN (model, likelihood, last_layer=False, subnetwork_indices=None, stochastic=False)

Implementation of the GGNInterface using asdfghjkl.

class AsdfghjklEF (model, likelihood, last_layer=False)

Implementation of the EFInterface using asdfghjkl.