Research map / Optimization / Nonconvex and smooth optimization
Projection onto Minkowski Sums with Application to Constrained Learning
Joong-Ho Won, Jason Xu, Kenneth Lange
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Minkowski projection block descent (Algorithm 1) used for overlapping group lasso proximal maps | overlapping group lasso (l1,p) with p=2 · synthetic, d from 10^3 to 10^6, g=10-100 | runtime vs SLEP | Improved |
| Minkowski projection method vs SLEP in high group count regime | overlapping group lasso · synthetic, d=10^6 | runtime | Hurt |
| Minkowski projection method vs SLEP in accuracy | overlapping group lasso · synthetic, varying dimension and groups | final objective accuracy | Improved |
| Minkowski projection method vs path algorithm, ADMM, Gurobi on constrained lasso | zero-sum and nonnegative constrained lasso · synthetic, up to (n,d)=(8000,16000) | runtime | Improved |
| Minkowski projection method vs ADMM sensitivity to sparsity level | constrained lasso · lambda/lambda_max 0.2 to 0.8 | runtime sensitivity | Improved |
| Viscosity penalty (rho>0) in block descent | projection onto polyhedral Minkowski sums (overlapping group lasso with p=infinity) · theory | convergence rate | Improved |
| Inexact projections (e.g., bisection for ball projection) in the block descent | l1,p minimization · empirical remark | accuracy/convergence | No clear effect |
Closest papers by meaning
- A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates (ICML 2017 · similarity 0.88)
- Dykstra's Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions (NeurIPS 2017 · similarity 0.88)
- Compact Convex Projections (JMLR 2018 · similarity 0.88)
- Fast Projection Onto Convex Smooth Constraints (ICML 2021 · similarity 0.87)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.86)
- On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity (ICML 2024 · similarity 0.86)
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.
