Version 1.7.1

For details, see the changelog.

Version 1.7.0

For details, see the changelog.

Version 1.6.0

See the changelog for details

Version 1.5.2

For details, refer to the changelog.

Version 1.5.1

For details, refer to the changelog.

Version 1.5.0

For details see the changelog.

Version 1.4.0

See the changelog for details.

Version 1.3.0

See the changelog for details.

1.2.0

Added

• Deprecated python3.5, tested compatibility with PyTorch 1.6.0 [PR]
• Support first-order extensions for Conv1d, Conv3d,
  ConvTranspose1d, ConvTranspose2d, ConvTranspose3d
  • extensions.BatchGrad [PR]
  • extensions.BatchL2Grad [PR]
  • extensions.SumGradSquared and extensions.Variance [PR]
  • Raise exceptions for unsupported exotic hyperparameters [PR1, PR2]
• New example: Backpropagating through BackPACK quantities [commit]
• New extensions in API: Block-diagonal curvature products
  • Exposed via extensions.HMP, extensions.GGNMP, extensions.PCHMP [PR]
  • Examples: Hutchinson trace estimation [PR] and Hessian-free optimization with CG [PR]

Fixed

• Add missing zero_grad in the diagonal GGN second-order optimization example [PR]

Internal

• Increased test coverage
  • New test suite for backpack.extensions [PR]
  • New test suite for backpack.core [PR]
• Implemented derivatives of the following operations in backpack.core
  • More activation functions [PR]
  • Conv1d, Conv3d [PR]
  • ConvTranspose1d, ConvTranspose2d, ConvTranspose3d [PR]
• Refactor firstorder extensions to share more code [PR1, PR2]
• Removed detachs to support differentiating through quantities [PR]

1.1.1

Added

• Improved documentation, moved to ReadTheDocs [PR1, PR2, PR3]
• Tested compatibility with PyTorch 1.5.0.
• Support 2nd-order backprop for vectors in MSELoss [PR]
• Sanity checks to raise warnings if the following are used.
  inplace modification [PR],
  unsupported loss parameters [PR],
  custom losses in 2nd-order backpropagation [PR]

Fixed

• Removed opt_einsum dependency [PR]
• Missing implementations and wrong backpropagation of KFRA for Conv2d, MaxPool2d, and AvgPool2d [PR]
• Remove try_view and use reshape to use PyTorch 1.4.0 improvements [PR]

Internal

• Docstring style [PR]