Concepts174

πŸ“šTheoryIntermediate

Complexity Theory

Complexity theory classifies problems by the resources required to solve or verify them, such as time and memory.

#complexity theory#p vs np#np-complete+12
πŸ“šTheoryIntermediate

Contrastive Learning Theory

Contrastive learning learns representations by pulling together positive pairs and pushing apart negatives using a softmax-based objective.

#contrastive learning#infonce#nt-xent+12
πŸ“šTheoryIntermediate

Bellman Equations

Bellman equations express how the value of a state or action equals immediate reward plus discounted value of what follows.

#bellman equation#value iteration#policy iteration+12
πŸ“šTheoryIntermediate

Attention Mechanism Theory

Attention computes a weighted sum of values V where the weights come from how similar queries Q are to keys K.

#attention#self-attention#multi-head attention+12
πŸ“šTheoryIntermediate

Scaling Laws

Scaling laws say that model loss typically follows a power law that improves predictably as you increase parameters, data, or compute.

#scaling laws#power law#chinchilla scaling+12
πŸ“šTheoryIntermediate

Universal Approximation Theorem

The Universal Approximation Theorem (UAT) says a feedforward neural network with one hidden layer and a non-polynomial activation (like sigmoid or ReLU) can approximate any continuous function on a compact set as closely as we want.

#universal approximation theorem#cybenko#hornik+12
πŸ“šTheoryIntermediate

Minimax Theorem

The Minimax Theorem states that in zero-sum two-player games with suitable convexity and compactness, the best guaranteed payoff for the maximizer equals the worst-case loss for the minimizer.

#minimax theorem#zero-sum games#saddle point+12
πŸ“šTheoryIntermediate

PAC Learning

PAC learning formalizes when a learner can probably (with probability at least 1βˆ’Ξ΄) and approximately (error at most Ξ΅) succeed using a polynomial number of samples.

#pac learning#agnostic learning#vc dimension+12
πŸ“šTheoryIntermediate

Bias-Variance Tradeoff

The bias–variance tradeoff explains how prediction error splits into bias squared, variance, and irreducible noise for squared loss.

#bias variance tradeoff#mse decomposition#polynomial regression+12
πŸ“šTheoryIntermediate

Game Theory

Game theory studies strategic decision-making among multiple players where each player’s payoff depends on everyone’s actions.

#game theory#nash equilibrium#mixed strategies+11
πŸ“šTheoryIntermediate

Lagrangian Duality

Lagrangian duality turns a constrained minimization problem into a related maximization problem that provides lower bounds on the original objective.

#lagrangian duality#kkt conditions#slater condition+11
πŸ“šTheoryIntermediate

Matrix Calculus

Matrix calculus extends ordinary calculus to functions whose inputs and outputs are vectors and matrices, letting you compute gradients, Jacobians, and Hessians systematically.

#matrix calculus#gradient#jacobian+12