Research map / Optimization / Nonconvex and smooth optimization
Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers
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 |
|---|---|---|---|
| Integrate Nesterov extrapolation with SVRG-style variance reduction in stochastic ADMM | ACC-SADMM · convex finite-sum with linear constraints (theory) | non-ergodic convergence rate | Helped |
| Use variance reduction without extrapolation (SAG/SVRG-ADMM) | VR-based SADMM · convex finite-sum with linear constraints (theory) | non-ergodic convergence rate | No clear effect |
| Nesterov-style extrapolation with snapshot-based inner loop on Lasso and graph-guided fused Lasso experiments | ACC-SADMM vs STOC-ADMM, SVRG-ADMM, SAG-ADMM, OPT-ADMM · a9a, covertype, mnist, dna (Lasso and Graph-Guided Fused Lasso) | objective gap vs effective passes | Helped |
| Use SVRG-ADMM/SAG-ADMM with theoretical step sizes instead of tuned ones | VR-based SADMM · Lasso experiments | objective gap vs effective passes | Hurt |
Closest papers by meaning
- Accelerated Variance Reduced Stochastic ADMM (AAAI 2017 · similarity 0.92)
- Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization (ICML 2019 · similarity 0.91)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.88)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.88)
- An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions (ICML 2025 · similarity 0.87)
- Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction (NeurIPS 2024 · 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.