Research map / Optimization / Nonconvex and smooth optimization
VFOSA: Variance-Reduced Fast Operator Splitting Algorithms for Generalized Equations
Quoc Tran-Dinh
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 SAGA instead of L-SVRG estimator (ablation) | VFOSA+ · Robust logistic regression, l1 regularizer (w8a, gisette) | relative residual norm over epochs | Improved |
| use L-SARAH instead of L-SVRG and SAGA estimators (ablation) | VFOSA+ · Robust logistic regression, l1 regularizer (w8a, gisette) | relative residual norm over epochs | Improved |
| use HSGD instead of the other three estimators (ablation) | VFOSA+ · Robust logistic regression, l1 regularizer (w8a, gisette) | relative residual norm over epochs | Improved |
| use biased estimators (L-SARAH, HSGD) instead of unbiased (L-SVRG, SAGA) (ablation) | VFOSA+ · Robust logistic regression, l1 regularizer (w8a, gisette) | relative residual norm over epochs | Improved |
| use L-SARAH and HSGD instead of L-SVRG and SAGA (ablation) | VFOSA+ · Robust logistic regression, l1 regularizer (mnist, a9a) | relative residual norm over epochs | Improved |
Closest papers by meaning
- Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations (ICML 2025 · similarity 0.91)
- Operator Splitting with Hamilton-Jacobi-based Proximals (ICML 2026 · similarity 0.87)
- GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization (ICML 2017 · similarity 0.87)
- Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient (ICML 2024 · similarity 0.86)
- A Unifying Framework for Variance-Reduced Algorithms for Findings Zeroes of Monotone operators (JMLR 2022 · similarity 0.85)
- Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs (ICML 2018 · 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.
