Research map / Optimization / Implicit bias and generalization
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models
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 ML-AMP rather than gradient flow for maximum-likelihood estimation | Spiked matrix-tensor model · p=3, Δp=1.0 | 1/Δ₂ threshold for algorithmic success: 1.97 -> 1.62 | Helped |
| Run gradient flow in a regime with spurious local minima | Gradient flow · Spiked matrix-tensor model | correlation with the signal | Helped |
| Increase Δ₂ toward the gradient-flow threshold | Gradient flow · Spiked matrix-tensor model | convergence time | Hurt |
| Treat landscape trivialization as a sufficient condition for fast gradient-flow optimization | Gradient flow · Spiked matrix-tensor model | convergence time | Hurt |
Closest papers by meaning
- Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models (NeurIPS 2019 · similarity 0.91)
- Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario (NeurIPS 2026 · similarity 0.88)
- The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank (AAAI 2024 · similarity 0.87)
- The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations (ICML 2025 · similarity 0.87)
- Free Decompression with Algebraic Spectral Curves (NeurIPS 2026 · similarity 0.86)
- No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths (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.