Research map / Optimization / Nonconvex and smooth optimization
Stochastic Variance Reduction Methods for Saddle-Point Problems
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 |
|---|---|---|---|
| uniform sampling for SAGA | SAGA on saddle-point problems · sido | convergence vs batch methods | No clear effect |
| non-uniform sampling instead of uniform | SAGA/SVRG on bilinear saddle-point problems · theory (complexity table) | complexity bound | Helped |
| Catalyst-style acceleration of SVRG (every log(1+tau) epochs update the anchor) | SVRG on saddle-point problems · sido, ill-conditioned problems | squared distance to optimizer vs passes | Helped |
| primal Nesterov-accelerated method (fba-primal) vs SAGA on primal for separable loss | rcv1 separable loss comparison · rcv1 | convergence speed | Hurt |
Closest papers by meaning
- Stochastic Variance Reduction for Nonconvex Optimization (ICML 2016 · similarity 0.89)
- Estimate Sequences for Variance-Reduced Stochastic Composite Optimization (ICML 2019 · similarity 0.89)
- A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates (ICML 2018 · similarity 0.89)
- Stochastic Variance-Reduced Cubic Regularized Newton Methods (ICML 2018 · similarity 0.89)
- Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure (NeurIPS 2017 · similarity 0.89)
- Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry (NeurIPS 2024 · 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.