Research map / Optimization / Implicit bias and generalization
Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
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 online (single-sample) SGD with stochastic noise from data instead of artificial noise injection for escaping unstable equilibria in ICA tensor decomposition | SGD for tensor-method ICA · theoretical analysis (ICA tensor decomposition) | escape from unstable equilibria | No clear effect |
| Analyze SGD in three phases (unstable OU escape, ODE traverse, stable OU convergence) rather than classical upper-bound analysis | SGD for ICA tensor decomposition · theoretical analysis | iteration count per phase | No clear effect |
Closest papers by meaning
- Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization (NeurIPS 2018 · similarity 0.89)
- The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations (ICML 2025 · similarity 0.88)
- High-dimensional Limit of SGD for Diagonal Linear Networks (NeurIPS 2026 · similarity 0.88)
- What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis (ICML 2024 · similarity 0.88)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 2025 · similarity 0.87)
- Demystifying SGD with Doubly Stochastic Gradients (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.