Concepts174

πŸ“šTheoryIntermediate

Singular Value Decomposition (SVD)

Singular Value Decomposition (SVD) factors any mΓ—n matrix A into A = UΞ£V^{T}, where U and V are orthogonal and Ξ£ is diagonal with nonnegative entries.

#singular value decomposition#svd#truncated svd+12
πŸ“šTheoryIntermediate

Convex Optimization

Convex optimization studies minimizing convex functions over convex sets, where every local minimum is guaranteed to be a global minimum.

#convex optimization#convex function#convex set+12
πŸ“šTheoryIntermediate

Eigenvalue Decomposition

Eigenvalue decomposition rewrites a square matrix as a change of basis that reveals how it stretches and rotates space.

#eigenvalue decomposition#spectral theorem#power iteration+12
πŸ“šTheoryIntermediate

Optimization Theory

Optimization theory studies how to choose variables to minimize or maximize an objective while respecting constraints.

#optimization#convex optimization#gradient descent+12
πŸ“šTheoryIntermediate

Linear Algebra Theory

Linear algebra studies vectors, linear combinations, and transformations that preserve addition and scalar multiplication.

#linear algebra#vector space#basis+12
πŸ“šTheoryIntermediate

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
πŸ“šTheoryIntermediate

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#berry-esseen#lindeberg+12
πŸ“šTheoryIntermediate

Probability Distributions

Probability distributions describe how random outcomes are spread across possible values and let us compute probabilities, expectations, and uncertainties.

#probability distributions#pmf#pdf+12
πŸ“šTheoryIntermediate

Probability Theory

Probability theory formalizes uncertainty using a sample space, events, and a probability measure that obeys clear axioms.

#probability measure#random variable#expectation+12
πŸ“šTheoryIntermediate

Mutual Information

Mutual Information (MI) measures how much knowing one random variable reduces uncertainty about another.

#mutual information#entropy#kl divergence+12
πŸ“šTheoryIntermediate

KL Divergence (Kullback-Leibler Divergence)

Kullback–Leibler (KL) divergence measures how one probability distribution P devotes probability mass differently from a reference distribution Q.

#kl divergence#kullback-leibler#cross-entropy+12
πŸ“šTheoryIntermediate

Shannon Entropy

Shannon entropy quantifies the average uncertainty or information content of a random variable in bits when using base-2 logarithms.

#shannon entropy#information gain#mutual information+12