AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Stochastic DCA with Variance Reduction and Applications in Machine Learning

Hoai An Le Thi, Hoang Phuc Hau Luu, Hoai Minh Le, Tao Pham Dinh

JMLR 2022 · Optimization › Nonconvex and smooth optimization · approach: Stochastic variance reduction · 2 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 sampling without replacement instead of with replacement in DCA-SAGA (ablation)DCA-SAGA · Nonnegative PCA, 10 LIBSVM datasetssuboptimality: DCA-SAGA-v2 usually below 10^-10; DCA-SAGA-v1 much worseImproved
use sampling without replacement in DCA-SAGA (ablation)DCA-SAGA · Group variable selection in multiclass logistic regressionobjective valueImproved
use sampling without replacement in DCA-SAGA (ablation)DCA-SAGA · Sparse linear regressionobjective valueImproved
use SVRG variant v2 instead of v1 in DCA-SVRG (ablation)DCA-SVRG · Nonnegative PCA, 10 LIBSVM datasetssuboptimalityNo clear effect
replace SDCA with DCA-SAGASDCA · Group variable selection in multiclass logistic regressionobjective gain: 0.71% up to 60.15%Improved
replace SDCA with DCA-SVRG-v1SDCA · Group variable selection in multiclass logistic regressionobjective gain: 0.56% to 54.73%Improved
replace DCA-SVRG-v1 with DCA-SAGADCA-SVRG-v1 · Sparse linear regressionobjective gain: 5.22%, 0.24%, 0.56% on cadata, sgemm product, YearPredictionMSDImproved
replace SDCA with DCA-SVRG-v1SDCA · Sparse linear regressionobjective gain: 2.11%, 11.45%, 0.98%Improved
use proximal operator directly (MB-SPG) instead of Moreau envelope (SSDC)SSDC · Sparse linear regressionobjective valueImproved
use DCA-SVRG instead of prox-SAGA/SDCA/prox-SGDstochastic baselines · Nonnegative PCA, 10 LIBSVM datasetssuboptimality: around 10^-15 vs SDCA slightly worse than prox-SAGA (<10^-5), prox-SGD stuck around 10^-5Improved

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