AI Paper Atlas

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

Global and Quadratic Convergence of Newton Hard-Thresholding Pursuit

Shenglong Zhou, Naihua Xiu, Hou-Duo Qi

JMLR 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees · 47 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 NHTP instead of HTP (restricted Newton step) on very sparse compressive sensingHTP · Compressive sensing Ex.2, n=25000, s=ceil(0.05n)CPU time (s): 36.93 -> 6.58Improved
use NHTP instead of HTP for recovery accuracyHTP · Compressive sensing Ex.2, n=25000, s=ceil(0.05n)average absolute error: 5.94e-14 -> 2.86e-14Improved
use NHTP instead of NIHT for recovery accuracyNIHT · Compressive sensing Ex.2, n=25000, s=ceil(0.05n)average absolute error: 1.01e-6 -> 2.86e-14Improved
use NHTP instead of greedy GP/OMP when solution is less sparseGP · Compressive sensing Ex.2, n=25000, s=ceil(0.05n)average absolute error: 1.24e-03 -> 2.86e-14Improved
use NHTP instead of GP/OMP when solution is very sparseOMP · Compressive sensing Ex.2, n=25000, s=ceil(0.01n)average absolute error: 1.12e-14 -> 2.47e-15No clear effect
use NHTP instead of other solvers on success rate, Gaussian matrix, s=22other CS solvers · Compressive sensing Ex.1, n=256, m=ceil(n/4)success rate: 90% vs less than 40%Improved
use NHTP instead of GraSP for time at s=ceil(0.05n)GraSP · Sparse logistic regression Ex.3, n=40000CPU time (s): 619.5 -> 25.41Improved
use NHTP instead of IIHT at s=ceil(0.05n)IIHT · Sparse logistic regression Ex.3, n=40000, s=ceil(0.05n)logistic loss: 4.92e-4 -> 5.81e-7Improved
use NHTP instead of IIHT at s=ceil(0.01n)IIHT · Sparse logistic regression Ex.3, n=40000, s=ceil(0.01n)logistic loss: 1.21e-1 -> 2.05e-1Hurt
use NHTP instead of GraSP on correlated data timeGraSP · Sparse logistic regression Ex.4, n=40000, s=ceil(0.05n)CPU time (s): 721.0 -> 22.46Improved
use NHTP instead of IIHT when sample size is largeIIHT · Sparse logistic regression Ex.4, n=256, s=ceil(0.05n)logistic loss: m/n >= 0.2Hurt
use NHTP instead of IIHT when sample size is smallIIHT · Sparse logistic regression Ex.4, n=256, s=ceil(0.05n)logistic loss: m/n < 0.2Improved

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