Research map / Optimization / Nonconvex and smooth optimization
SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points
Zhize Li
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 the recursive gradient estimator instead of the SVRG estimator | SSRGD versus SVRG-type algorithms · Nonconvex finite-sum, first-order | stochastic gradient complexity: $n^{2/3}/\epsilon^2$ to $n^{1/2}/\epsilon^2$ | Improved |
| Add occasional uniform perturbations when the gradient is small | SSRGD · Nonconvex finite-sum, second-order | stochastic gradient complexity: $\widetilde{O}(\frac{n^{1/2}}{\epsilon^2} +\frac{n^{1/2}}{\delta^4} + \frac{n}{\delta^3})$ | Improved |
| Add occasional uniform perturbations when the gradient is small | SSRGD · Nonconvex online, second-order | stochastic gradient complexity: $\widetilde{O}(\frac{1}{\epsilon^{3}}+\frac{1}{\epsilon^2\delta^3}+\frac{1}{\epsilon\delta^4})$ | Improved |
Closest papers by meaning
- Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization (JMLR 2022 · similarity 0.92)
- The Complexity of Finding Stationary Points with Stochastic Gradient Descent (ICML 2020 · similarity 0.90)
- Faster Gradient-Free Methods for Escaping Saddle Points (ICLR 2023 · similarity 0.90)
- First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time (NeurIPS 2018 · similarity 0.90)
- Escape saddle points by a simple gradient-descent based algorithm (NeurIPS 2021 · similarity 0.90)
- Second-Order Convergence in Private Stochastic Non-Convex Optimization (NeurIPS 2025 · similarity 0.89)
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.
