AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Dykstra's Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions

Ryan J Tibshirani

NeurIPS 2017 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 23 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
Apply block coordinate descent to the regularized regression problem with separable seminorm penaltiesRegularized regression · Dual best-approximation problemalgorithmic equivalenceImproved
Use ADMM on the best-approximation problem with two sets, one a linear subspace, and the stated initialization and parameterDykstra's algorithm · Two-set best-approximation problemalgorithmic equivalenceImproved
Transfer polyhedral Dykstra convergence analysis to cyclic coordinate descentLasso coordinate descent · Lassoasymptotic convergence rateImproved
Use parallel-Dykstra coordinate descent instead of serial coordinate descentRegularized regression with separable seminorm penalties · Regularized regressionconvergence to a solutionImproved
Use parallel-ADMM coordinate descent instead of serial coordinate descentRegularized regression with separable seminorm penalties · Regularized regressionconvergence to a solutionImproved
Increase the ADMM parameter in parallel-ADMM coordinate descentParallel-ADMM-CD · Lasso simulationssuboptimalityImproved
Use parallel coordinate updates rather than serial updates under the paper's hypothetical 10%-efficient parallel implementationParallel-Dykstra-CD and parallel-ADMM-CD · Lasso simulationssuboptimality versus parallelized iteration costImproved
Use parallel-Dykstra-CD rather than serial coordinate descentLasso · Lassoasymptotic convergence rateHurt
Extend the Dykstra-coordinate descent correspondence to Bregman projection and nonquadratic lossRegularized estimation · Nonquadratic-loss problemsalgorithmic equivalenceImproved
Use warm starts across a decreasing sequence of lasso tuning parametersLasso coordinate descent · Lassoiteration count to enter the linear-convergence phaseImproved

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