Optimation
score function/loss function
convex function
convex optimization
subgradient
optimization:
Method 1
core idea:iteative refinement
Blindfolded hiker analogy
Method 2
Random local Search
Method 3
Following the gradient
########################
Compute the gradient
method 1
numerical gradient
method 2
analytic gradient
computing the gradient analytically with Calculus
##############
Gradient Descent
Mini-batch gradient decsent
Stochastic Gradient Descent
score function/loss function
convex function
convex optimization
subgradient
optimization:
Method 1
core idea:iteative refinement
Blindfolded hiker analogy
Method 2
Random local Search
Method 3
Following the gradient
########################
Compute the gradient
method 1
numerical gradient
method 2
analytic gradient
computing the gradient analytically with Calculus
##############
Gradient Descent
Mini-batch gradient decsent
Stochastic Gradient Descent