You are training a house price prediction model with 5,000 training examples using Mini-Batch Gradient Descent (MBGD) of batch size = 32. Which of the following statements correctly describes how MBGD works and why it is widely used?

Question

Answer

MBGD performs about 156 updates per epoch, each using 32 houses, balancing efficiency (via vectorization) and stability (less noisy than SGD).

Answer

MBGD does not require a learning rate hyperparameter, since averaging over mini-batches eliminates the need for step size control.

Answer

MBGD performs only 1 update per epoch, using all 5,000 houses at once, giving deterministic but very slow convergence.

Answer

MBGD performs 5,000 updates per epoch, one for each training house, giving fast progress but highly noisy convergence.

Crowdly

You are training a house price prediction model with 5,000 training examples usi...

Want instant access to all verified answers on moodle.nu.edu.kz?