AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Dual Iterative Hard Thresholding

Xiao-Tong Yuan, Bo Liu, Lezi Wang, Qingshan Liu, Dimitris N. Metaxas

JMLR 2020 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 3 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 DIHT instead of primal IHT and HTP on ill-conditioned linear regressionDIHT · Sparse linear regression, condition number about 50, (d,k)=(500,50)primal objective and parameter estimation errorImproved
increase condition number of the design matrix (ablation)DIHT · Sparse linear regression, kappa in [1,200]optimal primal-dual gapNo clear effect
increase noise level sigma (ablation)DIHT · Sparse linear regression, sigma in [10^-3, 50]optimal primal-dual gapHurt
increase regularization strength lambda (ablation)DIHT · Sparse linear regression, lambda0 in {0.01,0.1,1}optimal primal-dual gapImproved
use DIHT and SDIHT instead of IHT, HTP and SVR-GHTDIHT/SDIHT · RCV1 and News20, smoothed hinge lossprimal loss versus running timeImproved
use stochastic dual updates (SDIHT) instead of batch DIHTDIHT · RCV1 and News20, smoothed hinge lossrunning time and epochs to comparable accuracy and primal-dual gapImproved

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