AI Paper Atlas

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

Fast Stagewise Sparse Factor Regression

Kun Chen, Ruipeng Dong, Wanwan Xu, Zemin Zheng

JMLR 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees

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 stagewise learning instead of ACS for sequential pursuitSeqACS · Simulation Model II SNR=0.5 p=400time (s): 12.47 -> 1.03Improved
use stagewise learning instead of ACS for sequential pursuitSeqACS · Simulation Model II SNR=0.5 p=400Er(XC) x10^3: 115.37 -> 57.48Improved
use stagewise learning with RRR initialization instead of ACSParACS(R) · Simulation Model II SNR=0.5 p=400time (s): 12.83 -> 0.51Improved
use stagewise learning with RRR initialization instead of ACSParACS(R) · Simulation Model II SNR=0.5 p=400Er(XC) x10^3: 106.39 -> 61.04Improved
use stagewise learning instead of ACSSeqACS · Yeast eQTL with marginal screeningtime (s): 29.84 -> 3.26Improved
use stagewise ParSTL(R) instead of RSSVDRSSVD · Yeast eQTL full datatime (s): 1330.67 -> 36.02Improved
use stagewise ParSTL(R) instead of SeqACSSeqACS · Yeast eQTL full dataMSE: 0.26 -> 0.22Improved
use sparse low-rank ParSTL(R) instead of plain RRRRRR · Yeast eQTL with marginal screeningMSE: 0.34 -> 0.21Improved
drop marginal screening, use all 3244 markers (ablation)ParSTL(R) · Yeast eQTLMSE: 0.21 -> 0.22Hurt
drop marginal screening, use all 3244 markersParSTL(R) · Yeast eQTLtime (s): 1.12 -> 36.02Hurt
use parallel pursuit instead of sequential pursuitACS · Simulation, sparser C*estimation accuracyImproved
use parallel instead of sequential pursuitACS · Simulation, less sparse C*estimation accuracyNo clear effect

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