Optimization & Training Dynamics · Problem 1 of 5
Implement AdamW from scratch in numpy for one parameter tensor.
Implement the function/class skeleton in the editor. Any correct approach is accepted.
import numpy as np
class AdamW:
def __init__(self, shape, lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0.01):
raise NotImplementedError
def step(self, theta, grad):
raise NotImplementedErrorReady when you are
Submit your solution and a structured review appears here — verdict, score, and concrete feedback. Any correct approach passes.
Implement AdamW from scratch in numpy for one parameter tensor.
Implement the function/class skeleton in the editor. Any correct approach is accepted.