Beta. Content is under active construction and has not been peer-reviewed. Report errors on
GitHub
.
Disclaimer
Theorem
Path
Curriculum
Paths
Demos
Diagnostic
Search
Quiz Hub
/
Log-Probability Computation
Log-Probability Computation
3 questions
Difficulty 2-3
View topic
Foundation
0 / 3
3 foundation
Adapts to your performance
1 / 3
foundation (2/10)
conceptual
Probabilistic models often compute log-probabilities rather than probabilities directly. What is the main numerical motivation?
Hide and think first
A.
Logs are computationally faster to compute than products on modern CPU hardware
B.
Working in log-space guarantees a smoother loss landscape for gradient descent optimization
C.
Log probabilities are always between 0 and 1, making them easier to interpret than raw probabilities
D.
Products of many small probabilities underflow to zero in floating point; logs turn products into sums that stay representable
Submit Answer