AI Paper Atlas

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

Legendre Decomposition for Tensors

Mahito Sugiyama, Hiroyuki Nakahara, Koji Tsuda

NeurIPS 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: Randomized tensor decomposition algorithms · 14 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 natural gradient instead of gradient descentLegendre decomposition · Synthetic 20 × 20 × 20 tensorrunning time: more than six orders of magnitude fasterImproved
Use natural gradient instead of gradient descentLegendre decomposition · Synthetic 20 × 20 × 20 tensoriterations to convergence: two or three iterations; more than 10^5 iterationsImproved
Use Legendre decomposition instead of nonnegative Tucker, nonnegative CP, or CP-APRTensor decomposition · Face image datasetRMSEMixed
Use Legendre decomposition instead of nonnegative Tucker, nonnegative CP, or CP-APRTensor decomposition · MNISTRMSEImproved
Remove zero entries from the sample space before decompositionLegendre decomposition · MNISTRMSEImproved
Use Legendre decomposition instead of Tucker and CP decompositionsTensor decomposition · Face image datasetrunning timeHurt
Use Legendre decomposition instead of Tucker and CP decompositionsTensor decomposition · MNISTrunning timeHurt

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