Module laplace.curvature.backpack
Classes
class BackPackInterface (model, likelihood, last_layer=False, subnetwork_indices=None)
-
Interface for Backpack backend.
Ancestors
Subclasses
Methods
def jacobians(self, x, enable_backprop=False)
-
Compute Jacobians \nabla_{\theta} f(x;\theta) at current parameter \theta using backpack's BatchGrad per output dimension. Note that BackPACK doesn't play well with torch.func, so this method has to be overridden.
Parameters
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
Returns
Js
:torch.Tensor
- Jacobians
(batch, parameters, outputs)
f
:torch.Tensor
- output function
(batch, outputs)
def gradients(self, x, y)
-
Compute gradients \nabla_\theta \ell(f(x;\theta, y) at current parameter \theta using Backpack's BatchGrad. Note that BackPACK doesn't play well with torch.func, so this method has to be overridden.
Parameters
x
:torch.Tensor
- input data
(batch, input_shape)
on compatible device with model. y
:torch.Tensor
Returns
Gs
:torch.Tensor
- gradients
(batch, parameters)
loss
:torch.Tensor
Inherited members
class BackPackGGN (model, likelihood, last_layer=False, subnetwork_indices=None, stochastic=False)
-
Implementation of the
GGNInterface
using Backpack.Ancestors
Inherited members
class BackPackEF (model, likelihood, last_layer=False, subnetwork_indices=None)
-
Implementation of
EFInterface
using Backpack.Ancestors
Inherited members