Research map / Optimization / Nonconvex and smooth optimization
Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent
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 |
|---|---|---|---|
| replace SVRG-style variance reduction with SARAH recursive estimators for inner function, Jacobian and gradient | VRSC-PG · finite-sum non-convex compositional optimization | IFO complexity bound: (n + m)2/3ε−2 -> (n + m)1/2ε−2 | Helped |
| replace SCVR recursive estimators with SARAH recursion in the online case | SCVR / SC-SCSG · online non-convex compositional optimization | IFO complexity bound: ε−3.6 -> ε−3 | Helped |
| use SARAH-Compositional instead of SCGD, ASC-PG and VRSC-PG | risk-averse portfolio management · six 25-portfolio datasets, N=25, T=7240 | objective gap vs IFO calls | Helped |
| use plain SCGD with small mini-batches instead of variance-reduced methods | SCGD · portfolio management | objective gap vs IFO calls | Hurt |
Closest papers by meaning
- Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization (NeurIPS 2024 · similarity 0.92)
- Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization (AAAI 2024 · similarity 0.90)
- Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms (ICML 2024 · similarity 0.90)
- Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization (NeurIPS 2025 · similarity 0.90)
- A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization (ICML 2025 · similarity 0.89)
- Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization (ICML 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.