Research map / Optimization / Nonconvex and smooth optimization
Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function
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 |
|---|---|---|---|
| use hybrid variance-reduced HSCG instead of ASC-PG | stochastic compositional gradient · Risk-averse portfolio optimization | objective value vs epochs | Helped |
| use HSCG instead of CIVR | variance-reduced compositional methods · Risk-averse portfolio optimization | objective value vs epochs | Helped |
| use HSCG instead of SCG and Prox-Linear | stochastic minimax model selection · rcv1 and url | objective value vs epochs | Helped |
| use HSCG instead of Prox-Linear | stochastic minimax model selection · covtype | objective value vs epochs | Hurt |
Closest papers by meaning
- Stochastic Variance Reduction for Nonconvex Optimization (ICML 2016 · similarity 0.91)
- Stochastic Nested Variance Reduction for Nonconvex Optimization (NeurIPS 2018 · similarity 0.91)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.91)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.89)
- Semi-infinite Nonconvex Constrained Min-Max Optimization (NeurIPS 2025 · similarity 0.88)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.88)
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.