AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Computing Higher Order Derivatives of Matrix and Tensor Expressions

Soeren Laue, Matthias Mitterreiter, Joachim Giesen

NeurIPS 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: Tensor network decompositions · 29 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
compute second order derivatives directly on tensor expressions (Ricci calculus) instead of row-by-row Hessian via gradient-times-basis-vectorautomatic differentiation framework · Hessian on CPUrunning timeImproved
same tensor-calculus approach on GPUautomatic differentiation framework · Hessian on GPUrunning timeImproved
use tensor calculus for first order derivatives vs existing frameworksautomatic differentiation framework · function value and gradient evaluationrunning timeNo clear effect
build expression graph with tensor calculus instead of TensorFlow/Theanoautomatic differentiation framework · second order derivative graph creationgraph construction time: a few seconds -> roughly 20 millisecondsImproved

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