LinkedIn·Machine Learning Engineer·Technical Phone Screen
- Walk through how Adam works, including its first and second moment estimates, the bias correction step, and the per-parameter update rule. Then explain why dividing by the square root of the second moment adapts the learning rate per parameter, how that connects to RMSProp, and what it means for sparse or unevenly scaled gradients.
“I got the mechanics down fine, m_t and v_t, bias correction, the update formula.”