Research map / Optimization / Implicit bias and generalization
Who is Afraid of Big Bad Minima? Analysis of gradient-flow 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 gradient flow with Δ₂ below Δ₂^GF | Gradient flow on the spiked matrix-tensor model · Spiked matrix-tensor model | correlation with the hidden signal | Helped |
| Use gradient flow with Δ₂ above Δ₂^GF | Gradient flow on the spiked matrix-tensor model · Spiked matrix-tensor model | correlation with the hidden signal | Hurt |
| Increase signal-to-noise ratio past the instability of threshold minima | Gradient flow on the spiked matrix-tensor model · Spiked matrix-tensor model | correlation with the hidden signal | Helped |
| Increase signal-to-noise ratio while spurious minima remain | Gradient flow on the spiked matrix-tensor model · Spiked matrix-tensor model with spurious local minima | gradient-flow success | Helped |
| Compare the gradient-flow threshold with the trivialization threshold | Gradient flow on the spiked matrix-tensor model · Spiked matrix-tensor model | noise threshold | Mixed |
| Increase signal-to-noise ratio beyond the gradient-flow threshold | Gradient flow on the spiked matrix-tensor model · Spiked matrix-tensor model | trapping time near threshold minima | Helped |
Closest papers by meaning
- Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models (ICML 2019 · similarity 0.91)
- On the Optimization Landscape of Tensor Decompositions (NeurIPS 2017 · similarity 0.88)
- The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations (ICML 2025 · similarity 0.88)
- No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths (ICML 2024 · similarity 0.87)
- Exploring Landscapes for Better Minima along Valleys (NeurIPS 2025 · similarity 0.87)
- SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures (NeurIPS 2025 · 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.