Dimer-Enhanced Optimization: A First-Order Approach to Escaping Saddle Points in Neural Network Training

26 July 2025

Papers citing "Dimer-Enhanced Optimization: A First-Order Approach to Escaping Saddle Points in Neural Network Training"

1 / 1 papers shown

Title
Escaping Saddle Points via Curvature-Calibrated Perturbations: A Complete Analysis with Explicit Constants and Empirical Validation Faruk Alpay Hamdi Alakkad 84 0 0 22 Aug 2025