Changelog and Road map¶
Put reference paper on Arxiv.
Fully document the inner C++ API and algorithms.
Provide R bindings.
Add support for tensor (and not just vector) variables.
Allow users to backprop through the
.max()reduction of a
Add support for the advanced indexing of
LazyTensors. Users should be able to extract sub-matrices as
LazyTensorsor genuine NumPy arrays / PyTorch tensors to perform e.g. Nyström approximation without having to implement twice the same kernel formula.
Add support for the block construction of
LazyTensors, using a
BlockLazyTensor([[A, B], [C, D]])syntax.
LazyTensors, allowing users to cast their symbolic operators as explicit matrices whenever possible.