Research map / Optimization / Nonconvex and smooth optimization
Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking
Isidoros Tziotis, Constantine Caramanis, Aryan Mokhtari
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 |
|---|---|---|---|
| inject noise near first-order stationary points (PDGT) instead of plain gradient tracking (D-GET) | Decentralized gradient tracking · MovieLens matrix factorization, 10 nodes, rank 20 | saddle escape time / loss | Improved |
| inject noise (PDGT vs D-GET) | Decentralized gradient tracking · MovieLens matrix factorization, 30 nodes, rank 30 | saddle escape time | Improved |
| run D-GET long enough instead of perturbing | D-GET · MovieLens, 30 nodes, rank 30 | final convergence | No clear effect |
| use larger stepsizes, noise radius and threshold than the theory prescribes | PDGT · MovieLens, 30 nodes | practical performance | Improved |
Closest papers by meaning
- DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity (ICLR 2025 · similarity 0.87)
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.87)
- Second-Order Convergence in Private Stochastic Non-Convex Optimization (NeurIPS 2025 · similarity 0.87)
- Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization (NeurIPS 2024 · similarity 0.86)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.86)
- Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods (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.
