AI Paper Atlas

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

A Non-commutative Extension of Lee-Seung's Algorithm for Positive Semidefinite Factorizations

Yong Sheng Soh, Antonios Varvitsiotis

NeurIPS 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization · 1 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
Run MMU with 50 random initializations for 500 iterations on a 20x20 random distance matrix with rank-2 PSD factorizationMMU algorithm · Random Euclidean distance matrix (n=20)normalized squared errorImproved
Use a 7-dimensional full PSD factorization instead of a 27-dimensional NMF to decompose a face imageMMU algorithm · CBCL Face Databaseinterpretability of learned building blocksHurt
Use a block-diagonal PSD factorization with 9 blocks of size 2 instead of a full 7-dimensional PSD factorization (ablation)MMU algorithm · CBCL Face Databaselocality of learned building blocksImproved
Learn a continuum of atoms from a single 2x2 block instead of finitely many NMF atomsMMU block-diagonal PSD factorization · CBCL Face Databaseexpressiveness of geometry capturedImproved
Initialize MMU with diagonal PSD matricesMMU algorithm · Theory (Section on NMF link)iterate structureImproved

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