Research map / Optimization / Nonconvex and smooth optimization
Stochastic Halpern Iteration with Variance Reduction for Stochastic Monotone Inclusions
Xufeng Cai, Chaobing Song, Cristóbal A Guzmán, Jelena Diakonikolas
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 PAGE instead of single-sample or mini-batch estimators (ablation) | E-Halpern · Robust least squares on superconductivity dataset | operator norm versus stochastic operator evaluations | Improved |
| Use Halpern or E-Halpern instead of GDA, extragradient, or Popov | Stochastic min-max methods · Robust least squares on superconductivity dataset | operator norm versus stochastic operator evaluations | Improved |
| Add restarts when the stochastic estimator norm halves (ablation) | E-Halpern · Robust least squares on superconductivity dataset | operator norm versus stochastic operator evaluations | Improved |
Closest papers by meaning
- Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions (ICLR 2024 · similarity 0.92)
- Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction (NeurIPS 2024 · similarity 0.87)
- Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates (NeurIPS 2026 · similarity 0.85)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.85)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.85)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 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.
