Research map / Optimization / Nonconvex and smooth optimization
Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data
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 projected SGD with Markovian (dependent) data instead of i.i.d. sampling in constrained smooth nonconvex optimization | projected SGD · constrained smooth nonconvex with dependent data | complexity for eps-stationarity: from O~(eps^-8) (prior SMM) to O~(eps^-4) | Helped |
| Replace stationary-interior assumption with none (iterates may lie on constraint boundary) for dependent-data analysis | projected SGD with dependent data · constrained smooth nonconvex | complexity | No clear effect |
| Use AdaGrad-norm step sizes instead of decaying schedule under dependent data | AdaGrad-norm · Online NMF on Caltech Facebook subgraph stream | reconstruction error vs time | Helped |
| Dataset change from Caltech to UCLA/Wisconsin for online NMF comparison of AdaGrad/PSGD/SMM | AdaGrad vs other methods · Online NMF on UCLA26 and Wisconsin87 | reconstruction error vs time | No clear effect |
Closest papers by meaning
- Stochastic Optimization with Arbitrary Recurrent Data Sampling (ICML 2024 · similarity 0.89)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · similarity 0.89)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.88)
- Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis (NeurIPS 2025 · similarity 0.88)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.88)
- Stochastic Optimization with Random Search (NeurIPS 2026 · 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.