Module adamw

AdamW (Adam with decoupled Weight Decay) optimizer

AdamW modifies the original Adam algorithm by decoupling weight decay from the gradient-based update. This leads to better generalization performance, especially in deep learning applications.

Structs

AdamWOptions

Options for AdamW optimization

Functions

minimize_adamw

AdamW optimizer implementation

minimize_adamw_cosine_restarts

AdamW with cosine annealing and restarts