Research map / Optimization / Nonconvex and smooth optimization
Stochastic Three-Composite Convex Minimization
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 stochastic gradient of smooth term with proximal operators of the two nonsmooth terms (S3CM) instead of deterministic three-operator splitting | Markowitz portfolio optimization · DJIA, NYSE, SP500, TSE, FF100 portfolio datasets | test objective convergence vs. deterministic 3-operator splitting | No clear effect |
| Stochastic gradient estimate with learning rate gamma_n = gamma0/(n+1) on SVM dual | Nonlinear SVM classification (a1a) · a1a | squared relative error | Helped |
| Stochastic gradient estimate on the smooth term with Theorem 2 learning rate | Markowitz portfolio optimization (FF100) · FF100 | squared relative distance to optimum | Helped |
Closest papers by meaning
- On the Almost Sure Convergence of the Stochastic Three Points Algorithm (ICLR 2025 · similarity 0.91)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.89)
- Stochastic Weakly Convex Optimization beyond Lipschitz Continuity (ICML 2024 · similarity 0.88)
- High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise (ICML 2024 · similarity 0.88)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.87)
- Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods (ICLR 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.