Research map / Optimization / Nonconvex and smooth optimization
Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems
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 direct stochastic proximal gradient (MB-SPG) instead of Moreau-envelope approximation | non-smooth non-convex regularized minimization, online setting · complexity analysis | complexity: O(ϵ−5) -> O(ϵ−4) | Helped |
| add SARAH/SPIDER recursive gradient estimator to MB-SPG (SPGR) | MB-SPG · complexity analysis, online setting | complexity: O(ϵ−4) -> O(ϵ−3) | Helped |
| use increasing mini-batch sizes instead of fixed size | MB-SPG · complexity analysis | complexity | Mixed |
| use SPGR instead of MB-SPG | regularized NLLS/TLS minimization · covtype, a9a, E2006, triazines | objective vs gradient computations | Helped |
| use SPGR instead of heuristic SGD and other baselines for quantized models | quantized NLLS model · mnist, news20, rcv1, w8a | testing accuracy | Helped |
Closest papers by meaning
- Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization (ICML 2019 · similarity 0.93)
- Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization (NeurIPS 2016 · similarity 0.91)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · similarity 0.90)
- A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization (NeurIPS 2018 · similarity 0.90)
- Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization (ICML 2025 · similarity 0.88)
- Non-convex Stochastic Composite Optimization with Polyak Momentum (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.