StackedML
Practice
Labs
Questions
Models
Pricing
Sign in
Questions
/
Optimization
/
Gradient Methods
/
Saddle points
← Previous
Next →
199.
Definition of Saddle Point
easy
What is a saddle point in the context of optimization?
A
A stationary point where the gradient is large but the loss is unusually low relative to neighboring points
B
A stationary point where the gradient is zero but the function curves upward in some directions and downward in others
C
A stationary point where the function is flat in all directions causing gradient descent to stall permanently
D
A stationary point where the gradient is zero and the function is at a local minimum in all directions
Sign in to verify your answer
← Back to Questions