On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “saddle-avoidance”

Global Convergence of Four-Layer Matrix Factorization under Random Initializationmath.OC

Gradient descent proves global convergence for 4-layer matrix factorization.

problem Global convergence of gradient descent on four-layer matrix factorization under random initialization.

method New techniques to show saddle-avoidance properties and extend eigenvalue theories.

result Polynomial-time global convergence guarantee for randomly initialized gradient descent on four-layer matrix factorization.

matrix factorization gradient descent global convergence four-layer saddle-avoidance

2025-11-13abs ↗pdf ↗

Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstructioncs.LG

Gradient descent with small random init mimics spectral methods for low-rank matrix recovery.

problem Reconstructing a low-rank matrix from few measurements.

method Gradient descent with small random initialization followed by a few iterations.

result Gradient descent from small random init converges to a well-generalizing solution.

low-rank matrix gradient descent spectral methods overparameterization generalization

2021-06-28abs ↗pdf ↗