AI Paper Atlas

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

Fast Exact Matrix Completion: A Unified Optimization Framework for Matrix Completion

Dimitris Bertsimas, Michael Lingzhi Li

JMLR 2020 · Learning theory and algorithms › Matrix and tensor methods · approach: Nonconvex low-rank and sparse optimization · 5 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 fastImpute instead of IMC on Netflix with side informationfastImpute · Netflix full 471,268x14,538 (side information)MAPE: 21.0% -> 20.7%Improved
use fastImpute instead of SIALS on Netflix without side informationfastImpute · Netflix full 471,268x14,538MAPE: 20.1% -> 13.8%Improved
use fastImpute instead of SIALS on full Netflix without side informationfastImpute · Netflix full 471,268x14,538runtime: 38256s -> 2098sImproved
use fastImpute instead of IMC on synthetic data with 95% missingfastImpute · Synthetic n=1e4, m=1e3, p=100, k=5MAPE: 2.5% -> 0.1%Improved
use stochastic fastImpute instead of full-gradient projImpute (ablation)fastImpute · Synthetic n=1e6, m=1e3, p=100, k=5runtime: 6035s -> 390sImproved
use fastImpute instead of SIALS, SISVD, MFSGD and GROUSE on large realistic combinationsfastImpute · Synthetic, no side informationruntime and MAPE: -90% T and -71% MAPE vs SIALS; -99% and -95% vs SISVD; -96% and -45% vs MFSGD; -81% and -15% vs GROUSEImproved
increase the fraction of missing entries from 20% to 95%IMC · Synthetic with side informationMAPE: 0.01% -> 2.5%Hurt
increase the fraction of missing entries from 20% to 95%SIALS · Synthetic without side informationMAPE: 0.6% -> 12.7%Hurt
increase the fraction of missing entries from 20% to 95%fastImpute · Synthetic with side informationMAPE: 0.7% -> 0.1%Improved
increase n (matrix size) toward 1e6MFSGD · Synthetic without side informationMAPE: 2.1% -> 7.0%Hurt
increase n from 1e3 to 1e6fastImpute · Synthetic without side informationMAPE: 3.5% -> 2.1%Improved
increase true rank k from 5 to 30fastImpute · Synthetic without side informationruntime: 4.2s -> 49.5sMixed

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