StackedML
Practice
Labs
Questions
Models
Pricing
Sign in
Questions
/
Optimization
/
Gradient Methods
/
Convex vs non-convex
← Previous
Next →
141.
Convex Loss Functions in ML
easy
Which of the following loss functions used in machine learning is convex?
A
Cross-entropy loss for a deep neural network, since it is defined as a sum of log probabilities
B
Hinge loss for a nonlinear SVM with an RBF kernel, since it uses a margin-based linear boundary
C
Mean absolute error for a neural network, since absolute values produce a piecewise linear convex surface
D
Mean squared error for linear regression, since it forms a bowl-shaped paraboloid over the parameter space
Sign in to verify your answer
← Back to Questions