Gradient descent in some simple settings
arXiv:1808.04839v22 citations
AI Analysis
This is an incremental study for researchers interested in basic optimization dynamics.
The paper investigates how noise affects gradient descent trajectories through computer experiments on simple functions, observing that noise can alter the path of gradient descent.
In this note, we observe the behavior of gradient flow and discrete and noisy gradient descent in some simple settings. It is commonly noted that addition of noise to gradient descent can affect the trajectory of gradient descent. Here, we run some computer experiments for gradient descent on some simple functions, and observe this principle in some concrete examples.