The reparameterization trick allows:
Answer options
A
Sampling without blocking gradients
B
Exact analytical integrals always
C
Avoiding any randomness
D
Using RNNs instead
Correct answer: Sampling without blocking gradients
Explanation
Quick AnswerThe correct answer is Sampling without blocking gradients because it directly addresses the core logic of Generative AI.
The reparameterization trick moves randomness (ε ~ N(0,I)) outside the network path (z = μ + σ⊙ε), enabling gradients to flow through the sampling operation during backpropagation.