CompTIA DataX DY0-001 (V1) Practice Question

A machine learning engineer is training a deep neural network on a massive dataset characterized by a highly non-convex loss surface. The engineer has chosen to use Stochastic Gradient Descent (SGD) instead of Batch Gradient Descent (BGD). Which statement best explains a key advantage of SGD in this specific context?

  • SGD guarantees a faster and more stable convergence to the global minimum by avoiding the noisy gradients associated with BGD.

  • SGD reduces the learning rate automatically during training, which leads to a more direct path towards the minimum of the loss function.

  • The parameter updates in SGD are computationally heavier per epoch and provide a more accurate gradient estimation than BGD.

  • The high variance in parameter updates, resulting from using a single sample, can help the model escape shallow local minima.

CompTIA DataX DY0-001 (V1)
Machine Learning
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

SAVE $64
$529.00 $465.00
Bash, the Crucial Exams Chat Bot
AI Bot