AI Paper Atlas

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

Algebraic Variety Models for High-Rank Matrix Completion

Greg Ongie, Rebecca Willett, Robert D. Nowak, Laura Balzano

ICML 2017 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization · 32 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 variety-based matrix completion (VMC) instead of low-rank matrix completionSynthetic union-of-subspaces data · Synthetic union of subspacessuccessful completion rateImproved
Use VMC instead of LRMC or LRMC-NCVXSynthetic nonlinear variety data · Synthetic parametric curves and surfacessuccessful completion rateImproved
Use VMC+SSC instead of LRMC+SSCHopkins 155 motion segmentation · Hopkins 155clustering errorMixed
Use VMC+SSC instead of SSC-EWZFHopkins 155 motion segmentation · Hopkins 155clustering errorImproved
Use VMC instead of LRMC or LRMC-NCVXMotion capture completion · CMU Mocap subject 56, trial 6completion errorImproved
Use polynomial feature degree 2 rather than degree 3 (ablation)VMC · CMU Mocap subject 56, trial 6, large missing ratescompletion errorImproved
Use polynomial feature degree 2 rather than degree 3 (ablation)VMC · CMU Mocap subject 56, trial 6, small missing ratescompletion errorNo clear effect
Use polynomial feature degree 2 or 3 rather than the original-space linear model (ablation)VMC versus LRMC and LRMC-NCVX · Synthetic union of subspacessuccessful completion rateImproved

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