Autograd mechanics

Autograd mechanics.

Type

Software

Intellectual base

Primary research

Link

https://docs.pytorch.org/docs/main/notes/autograd.html

Cited by

1 citation across 1 artifact.

Domain-specific

• Automatic Differentiation
  • JAX exposes both JVP and VJP transformations and composes them for Hessian–vector products; PyTorch's autograd supplies reverse-mode graph differentiation and a developing forward-mode interface.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Links previously used in the corpus

Before the registry existed this work was also linked 1 other way.

• https://docs.pytorch.org/docs/main/autograd.html ×1

Registry ID ref:ed6da562ec08 · see in the full table