AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming

Bart van Merrienboer, Dan Moldovan, Alexander Wiltschko

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Tangent's source-code-transformed derivative instead of PyTorch'sScalar function with a tight loop · Tight scalar loopruntime speed improvement: approximately 30% fasterImproved
Lazily initialize gradients with ZeroGrad rather than allocating zero arraysTangent · Array gradient accumulationruntime overheadImproved
Apply static dead-code elimination and algebraic simplification to generated adjointsTangent · Generated adjointsunnecessary computationImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy