AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Stochastic subgradient for composite convex optimization with functional constraints

Ion Necoara, Nitesh Kumar Singh

JMLR 2022 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods

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 robust (rho>0) instead of nominal (rho=0) formulationSSP sparse SVM · COVID CT test, class-independent cov, lambda=0.3test accuracy: 159, 64.1% -> 198, 79.8%Improved
use robust instead of nominal formulationSSP sparse SVM · COVID CT test, class-dependent cov, lambda=0.2test accuracy: 198, 79.8% -> 200, 80.6%No clear effect
use robust instead of nominal formulationSSP sparse SVM · COVID CT test, class-dependent cov, lambda=0.1test accuracy: 166, 66.9% -> 180, 72.5%Improved
use robust instead of nominal formulationSSP sparse SVM · COVID CT test, class-independent cov, lambda=0.2test accuracy: 183, 73.8% -> 200, 80.6%Improved
use SSP-LS instead of Leventhal-Lewis algorithmleast-squares solver · Random least-squares m=9000,p=10^5,n=10^4, delta=beta=1.96epochs: 213 -> 42Improved
use SSP-LS instead of Leventhal-Lewis algorithmleast-squares solver · Random least-squares m=9000,p=11000,n=10^5epochs: 23 -> 19No clear effect
increase delta=beta from 0.96 to 1.96 (ablation)SSP-LS · Random least-squares m=9000,p=9000,n=10^4epochs: 1688 -> 1028Improved
increase delta=beta from 0.96 to 1.96 (ablation)Leventhal-Lewis · Random least-squares m=9000,p=9000,n=10^4epochs: 1700 -> 1662No clear effect
use SSP-LS instead of Leventhal-Lewisleast-squares solver · Netlib LP fit2p (3000x13525)cpu time (s): 2188.3 -> 65.7Improved
use SSP-LS instead of Matlab lsqlinleast-squares solver · Netlib LP qap12 (3193x8856)cpu time (s): 3998.4 -> 374.1Improved
use SSP-LS instead of Matlab lsqlinleast-squares solver · Netlib LP afiro (21x51)cpu time (s): 0.09 -> 1.9Hurt
use SSP-LS instead of Matlab lsqlinleast-squares solver · Netlib LP osa_07 (1118x25067)cpu time (s): 3437.1 -> 3169.8No 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