FRACTALS IN NEURAL NETWORKS
— Simone Conradi (@S_Conradi) July 23, 2026
Hyperparameter tuning feels like navigating a coastline. Turns out that's literally true: the boundary between learning rates that train and ones that diverge is a fractal.
Why? Gradient descent is an iterated map, θ → θ − η∇L(θ), exactly like z… pic.twitter.com/kRz7cSd5dp
No comments:
Post a Comment