TorchLean API

NN.Proofs.Autograd.Runtime.Link.BackwardLeaves

Dense Backward Pass on Leaf Tapes #

Lowering an empty graph produces a tape that contains only leaf nodes. This file shows that the runtime dense reverse loop is the identity on such a tape: every leaf's backward returns no contributions, so each step performs its bookkeeping checks and returns the gradient array unchanged. This is the nil case shared by the Graph and GraphData backward-link theorems.

The node stored at index n of a leaf-only tape is the leaf of the n-th input tensor.

One runtime backward step at a leaf leaves the dense gradient array unchanged.

The runtime backward loop over a leaf-only tape is the identity on the gradient array.