2018/09/14 by Y. Cooper, Cooper, Y.
Engineering · Mathematics · #Advanced Numerical Analysis Techniques #Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Mathematics #Geometric Analysis and Curvature Flows #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
paper · pdf · doi:10.48550/arxiv.1809.05527
openalex publication_date 2018/09/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We consider the behavior of gradient flow and of discrete and noisy gradient descent. It is commonly noted that the addition of noise to the process of discrete gradient descent can affect the trajectory of gradient descent. In previous work, we observed such effects. There, we considered the case where the minima had codimension 1. In this note, we do some computer experiments and observe the behavior of noisy gradient descent in the more complex setting of minima of higher codimension.