AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Unified Methods for Exploiting Piecewise Linear Structure in Convex Optimization

Tyler B Johnson, Carlos Guestrin

NeurIPS 2016 · 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
add working sets (Algorithm 1) to dual coordinate ascentDCA · Group lasso, insurance claims, m=1600relative suboptimality and support set precision vs timeImproved
add working sets (Algorithm 1) to dual coordinate ascentDCA · Group lasso, m=100relative suboptimality and support set precision vs timeImproved
add piecewise screening (Theorem 3.4) to dual coordinate ascentDCA · Group lasso, m=100convergence timeImproved
add piecewise screening (Theorem 3.4) to dual coordinate ascentDCA · Group lasso, m=1600convergence timeNo clear effect
scale number of groups m from 100 to 400 to 1600DCA + piecewise screening · Group lassoscreening effectiveness: m = 100 -> 1600Hurt
add working sets (Algorithm 1) to dual coordinate ascentDCA · Linear SVM, Higgs, m=10^4, 10^5, 10^6relative suboptimality vs timeImproved
add piecewise screening (Theorem 3.4) to dual coordinate ascentDCA · Linear SVM, Higgs, large mrelative suboptimality vs timeNo clear effect
increase number of training examples mDCA + piecewise screening · Linear SVM, Higgsfraction of examples screened near best C: m = 10^4 -> 10^6Hurt
add piecewise screening on top of working sets (ablation)DCA + working sets · Group lasso and linear SVMconvergence timeNo clear effect
replace gap screening with piecewise screening (Theorem 3.4)DCA + screening · Group lassoconvergence timeImproved

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