Concepts152

Groups

Gradient Descent Convergence Theory

Gradient descent updates parameters by stepping opposite the gradient: x_{t+1} = x_t - \eta \nabla f(x_t).

#gradient descent#convergence rate#l-smooth+12

Central Limit Theorem

The Central Limit Theorem (CLT) says that the sum or average of many independent, identically distributed variables with finite variance becomes approximately normal (Gaussian).

#central limit theorem

9 10 11 12 13

Concepts152

Gradient Descent Convergence Theory

Central Limit Theorem

Probability Distributions

Probability Theory

Mutual Information

KL Divergence (Kullback-Leibler Divergence)

Shannon Entropy

Information Theory