Research map / Optimization / Nonconvex and smooth optimization
Fast Nonsmooth Regularized Risk Minimization with Continuation
Shuai Zheng, Ruiliang Zhang, James T. Kwok
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 |
|---|---|---|---|
| use continuation instead of a fixed smoothing parameter (ablation) | CNS-NA and CNS-A · rcv1 / YearPredictionMSD, strongly convex | convergence speed | Improved |
| smaller fixed smoothing parameter (1e-3 vs 1e-2) without continuation (ablation) | fixed-smoothing variants · rcv1 / YearPredictionMSD, strongly convex | convergence speed | Hurt |
| smaller fixed smoothing parameter (1e-3 vs 1e-2) without continuation (ablation) | fixed-smoothing variants · rcv1 / YearPredictionMSD, strongly convex | final solution quality | Improved |
| use continuation instead of fixed smoothing (ablation) | CNS-NA and CNS-A · rcv1 / YearPredictionMSD, general convex | convergence speed | Improved |
| accelerated proximal SVRG instead of proximal SVRG as stage solver | CNS · rcv1 / YearPredictionMSD, strongly convex | objective vs CPU time | Improved |
| CNS-NA instead of FOBOS and RDA | stochastic composite optimization · rcv1 / YearPredictionMSD, strongly convex | convergence speed | Improved |
| CNS-A instead of FOBOS, RDA and Poly-SGD | stochastic composite optimization · rcv1 / YearPredictionMSD, general convex | convergence speed | Improved |
| RDA (uses composite structure) instead of Poly-SGD | baselines · rcv1 / YearPredictionMSD, general convex | convergence speed | Improved |
| Poly-SGD instead of FOBOS and RDA | baselines · rcv1 / YearPredictionMSD, strongly convex | convergence speed | Improved |
Closest papers by meaning
- Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization (ICML 2019 · similarity 0.89)
- Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems (NeurIPS 2019 · similarity 0.88)
- On Graduated Optimization for Stochastic Non-Convex Problems (ICML 2016 · similarity 0.87)
- Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$ (NeurIPS 2025 · similarity 0.87)
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.86)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · similarity 0.85)
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.
