AdamW Update Step

Implement one AdamW update with bias correction and decoupled weight decay. A free ML coding interview task on NudgeCode: write it in Python and check it with tests in your browser. Medium · Optimization, AdamW.

Implement a functional AdamW step returning (param_new, m_new, v_new) without mutating inputs. Update moments, apply bias correction, then apply decoupled weight decay directly to parameters rather than adding it to the gradient.