Research map / Optimization / Nonconvex and smooth optimization
Inexact Proximal Gradient Methods for Non-Convex and Non-Smooth 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 inexact rather than exact proximal operators | IPG, AIPG, and nmAIPG · Robust OSCAR | running time: more than 100 folds speedup | Helped |
| Use inexact rather than exact proximal operators | IPG, AIPG, and nmAIPG · Robust OSCAR | convergence rate by iteration | No clear effect |
| Use accelerated rather than basic proximal gradient | APG and AIPG · Robust OSCAR | convergence rate by iteration | Helped |
| Use inexact rather than exact proximal operators | IPG, AIPG, and nmAIPG · Social Link Prediction | running time | Helped |
| Use inexact rather than exact proximal operators | IPG, AIPG, and nmAIPG · Social Link Prediction | convergence rate by iteration | No clear effect |
| Use an inexact subgradient solver for the proximal subproblem | IPG, AIPG, and nmAIPG · Robust Trace Lasso | proximal-gradient algorithm availability | Helped |
| Allow inexact proximal steps with suitably decreasing errors | IPG · Non-convex optimization | convergence rate: O(\frac{1}{T}) | Helped |
| Allow inexact proximal steps under the stated KL and error conditions | AIPG · Non-convex optimization | convergence behavior | Helped |
Closest papers by meaning
- Adaptive Proximal Gradient Method for Convex Optimization (NeurIPS 2024 · similarity 0.89)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · similarity 0.87)
- Adaptive Proximal Gradient Methods Are Universal Without Approximation (ICML 2024 · similarity 0.87)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.87)
- Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions (ICML 2024 · similarity 0.87)
- A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order Oracles (ICML 2024 · similarity 0.86)
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.