List view
`laplace-torch` v0.3 aims to bring extensive support to diffusion models. These models are challenging due to their (often images) output dimensionality. Considering that the linearized Laplace requires the `(n_outputs, n_params)`-shaped Jacobians, this can be very challenging (e.g. images have `n_outputs = width * height`). All features we aim for are: - [ ] Efficient, universal, ultimate Jacobian backend - [ ] Functional Laplace with subset-of-data support - [ ] Heteroskedastic Laplace - [ ] Fast last-layer predictive
Overdue by 4 month(s)•Due by February 2, 2025•3/27 issues closed