TorchLean API

NN.Proofs.RuntimeApprox.NF.BackwardOps.Linalg

Linear Algebra NF Reverse Nodes #

Reverse-mode approximation nodes for matrix-vector and matrix-matrix multiplication.

Internal spelling of axis-one insertion used repeatedly in outer-product formulas.

Instances For

    The internal axis-one spelling is an exact shape operation.

    Reverse node for matrix-vector multiplication (matVecMulSpec).

    VJP uses the standard adjoint identities: δW = δ ⊗ x and δx = Wᵀ δ (expressed in tensor form), with NF error bounds layered over the primitive ops.

    Instances For

      Reverse node for matrix multiplication (matMulSpec).

      VJP uses the standard identities δA = δC * Bᵀ and δB = Aᵀ * δC (in appropriate shapes), with NF error bounds layered over the primitive ops.

      Instances For