StackedML
Practice
Labs
Questions
Models
Pricing
Sign in
Questions
/
Supervised Learning
/
Other Models
/
KNN (distance metrics)
← Previous
Next →
487.
Manhattan vs Euclidean in High Dimensions
medium
Manhattan distance is preferred over Euclidean distance in some high-dimensional settings. Why?
A
Manhattan distance concentrates less than Euclidean distance in high dimensions, making it more discriminative
B
Manhattan distance ignores diagonal relationships between features, reducing sensitivity to correlated dimensions
C
Manhattan distance is scale-invariant and does not require feature normalization before use
D
Manhattan distance is always faster to compute than Euclidean distance regardless of dimensionality
Sign in to verify your answer
← Back to Questions