Research map / Optimization / Nonconvex and smooth optimization
Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization
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 coordinate smoothing gradient estimation instead of Gaussian smoothing (ablation) | ZO-ProxSVRG and ZO-ProxSAGA · Black-box binary classification and black-box DNN adversarial attacks | objective value and attack loss | Helped |
| Add SVRG or SAGA variance reduction to ZO-ProxSGD (ablation) | Black-box DNN adversarial attacks · Black-box DNN adversarial attacks | objective value and attack loss | Helped |
| Use SAGA instead of SVRG (ablation) | CooSGE methods · Black-box binary classification | objective value and test loss | Helped |
| Use CooSGE instead of GauSGE (ablation) | ZO-ProxSVRG and ZO-ProxSAGA · Nonconvex nonsmooth composite optimization | convergence rate: O(\frac{d}{T}) vs O(\frac{d}{T} + d\sigma^2) | Helped |
| Add SVRG or SAGA variance reduction to the stochastic proximal gradient-free method | RSPGF · Nonconvex nonsmooth composite optimization | convergence rate: O(\frac{1}{\sqrt{T}}) to O(\frac{1}{T}) | Helped |
Closest papers by meaning
- A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization (NeurIPS 2018 · similarity 0.93)
- Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization (NeurIPS 2016 · similarity 0.91)
- Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization (ICML 2019 · similarity 0.90)
- Gradient-Free Method for Heavily Constrained Nonconvex Optimization (ICML 2022 · similarity 0.89)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.87)
- Non-convex Stochastic Composite Optimization with Polyak Momentum (ICML 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.