Module reverse_mode

Reverse-mode automatic differentiation (backpropagation)

Reverse-mode AD is efficient for computing derivatives when the number of output variables is small (typically 1 for optimization). It builds a computational graph and then propagates derivatives backwards.

Structs

ComputationGraph

Computational graph for reverse-mode AD

ReverseADOptions

Options for reverse-mode automatic differentiation

ReverseVariable

Variable in the computational graph for reverse-mode AD

Functions

add

Addition operation on computation graph

cos

Cosine operation on computation graph

div

Division operation on computation graph

exp

Exponential operation on computation graph

is_reverse_mode_efficient

Check if reverse mode is preferred for the given problem dimensions

ln

Natural logarithm operation on computation graph

mul

Multiplication operation on computation graph

powi

Power operation (x^n) on computation graph

reverse_gauss_newton_hessian

Gauss-Newton Hessian approximation using reverse-mode AD

reverse_gradient

Compute gradient using reverse-mode automatic differentiation

reverse_gradient_with_tape

Simple reverse-mode gradient computation using a basic tape

reverse_hessian

Compute Hessian using reverse-mode automatic differentiation

reverse_vjp

Vector-Jacobian product using reverse-mode AD

sin

Sine operation on computation graph

sub

Subtraction operation on computation graph