backward: Run backward pass from a scalar loss tensor

In ggmlR: 'GGML' Tensor Operations for Machine Learning

Run backward pass from a scalar loss tensor

Description

Traverses the gradient tape in reverse and accumulates gradients into tensor$grad for all leaf tensors with requires_grad = TRUE.

Usage

backward(loss)

Arguments

loss	Scalar ag_tensor

Value

Named environment: tensor id -> gradient matrix (for use by optimizer$step)

Examples

w <- ag_param(matrix(runif(4), 2, 2))
x <- ag_tensor(matrix(c(1, 2), 2, 1))
y <- ag_tensor(matrix(c(0, 1), 2, 1))
with_grad_tape({
  out  <- ag_matmul(w, x)
  loss <- ag_mse_loss(out, y)
})
grads <- backward(loss)

ggmlR documentation built on July 14, 2026, 1:08 a.m.