Research map / Optimization / Nonconvex and smooth optimization
Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add SVRG-style variance reduction to stochastic gradient hard thresholding (SGHT -> SVR-GHT) | SGHT · Simulated sparse regression, Sigma_ij=0.5, (n,b)=(10000,1) | relative estimation error: 0.21676 -> 0.02614 | Helped |
| add variance reduction (SGHT -> SVR-GHT) | SGHT · Simulated sparse regression, Sigma_ij=0.1, (n,b)=(200,50) | relative estimation error: 0.06412 -> 0.00970 | Helped |
| add variance reduction (SGHT -> SVR-GHT) | SGHT · RCV1 GCAT, (n,b)=(100,50) | misclassification rate: 0.09142 -> 0.03444 | Helped |
| replace full-gradient GHT with SVR-GHT | GHT · Simulated sparse regression, Sigma_ij=0.1, (n,b)=(10000,1) | relative estimation error at optimal step size: 0.00851 -> 0.00968 | No clear effect |
| replace full-gradient GHT with SVR-GHT | GHT · Simulated data and RCV1 | convergence speed in passes over data | Helped |
Closest papers by meaning
- Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function (NeurIPS 2020 · similarity 0.90)
- Stochastic Variance Reduction for Nonconvex Optimization (ICML 2016 · similarity 0.90)
- An Effective Hard Thresholding Method Based on Stochastic Variance Reduction for Nonconvex Sparse Learning (AAAI 2020 · similarity 0.90)
- Stochastic Nested Variance Reduction for Nonconvex Optimization (NeurIPS 2018 · similarity 0.90)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.87)
- Stochastic Optimization with Random Search (NeurIPS 2026 · similarity 0.87)
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.