Contractive autoencoder - A contractive autoencoder is an autoencoder trained to reconstruct its inputs while discouraging its encoded representation from changing sharply under...
Contrastive divergence - Contrastive divergence, often abbreviated CD, is an approximate learning method for certain probabilistic models, especially energy-based models such as...
Control as inference - Control as inference is a framework that expresses action selection as probabilistic inference in a model linking states, actions, dynamics, and preferences.
Correlated topic model - A correlated topic model, or CTM, is a probabilistic topic model that uses a logistic-normal distribution for a document's topic proportions.
Coupling flow - A coupling flow is a normalizing flow built from invertible coupling transformations.
Covariance graph - A covariance graph is a graphical representation of marginal independence assumptions, commonly expressed through zeros in a Gaussian covariance matrix.
Covariance matrix adaptation evolution strategy - Covariance matrix adaptation evolution strategy, or CMA-ES, is a randomized method for optimizing functions of continuous parameters without requiring their...
Data processing inequality - The data processing inequality states that processing an observation cannot increase its mutual information about an upstream variable when the processing...
Data tempering - Data tempering is a Bayesian computational strategy that moves through a sequence of posterior distributions by gradually incorporating observations or...
Deadly triad in reinforcement learning - The deadly triad in reinforcement learning is the combination of function approximation, bootstrapping, and off-policy learning.
Deep ensemble - A deep ensemble combines predictions from several trained deep neural networks.
Deep Gaussian process - A deep Gaussian process is a probabilistic model that composes multiple mappings governed by Gaussian processes.
Deep kernel learning - Deep kernel learning combines a learned deep neural representation with a kernel method.
Deep Markov model - A deep Markov model is a probabilistic sequence model with latent states whose transition or observation distributions are parameterized by neural networks.
Deformable parts model - A deformable parts model detects objects by combining evidence for an overall object pattern with evidence for several movable parts.
Denoising diffusion probabilistic model - A denoising diffusion probabilistic model, or DDPM, generates data through a learned sequence of denoising transitions.
Denoising score matching - Denoising score matching trains a model to estimate the gradient of a noisy data distribution's log density by using clean examples and deliberately...
Density kernel - A density kernel is a weighting function used to spread an observation's contribution over nearby locations when estimating a probability density.
Deterministic policy gradient - A deterministic policy gradient is the derivative used to improve a policy that chooses a specific continuous action for each state.
Deterministic training conditional approximation - The deterministic training conditional approximation, or DTC, is a sparse Gaussian process approximation that makes training function values deterministic...
Diagonal linear discriminant analysis - Diagonal linear discriminant analysis, or DLDA, is a classification method that uses class-specific means and a shared diagonal covariance matrix.
Differentiable cross-entropy method - The differentiable cross-entropy method, or DCEM, is a differentiable variant of a sampling-based optimization method.
Dirichlet-multinomial model - A Dirichlet-multinomial model combines a Dirichlet distribution over category probabilities with a multinomial distribution over counts.
Discrete denoising diffusion probabilistic model - A discrete denoising diffusion probabilistic model, often abbreviated D3PM, generates discrete data by learning to reverse a gradual categorical corruption...
Discrete variational autoencoder - A discrete variational autoencoder is a variational generative model that uses discrete latent variables, such as categorical choices or binary states, to...
Distributionally robust optimization - Distributionally robust optimization (DRO) chooses a model or decision by minimizing its worst expected loss across a specified set of possible probability...
Domain generalization - Domain generalization is the task of learning from available environments so that a model works well in a new environment whose data were not used to train...
Double machine learning - Double machine learning (DML), also called double/debiased machine learning, is a framework for estimating a target statistical or causal parameter while...
Double Q-learning - Double Q-learning is an off-policy reinforcement-learning method that uses two action-value estimates to separate choosing a promising next action from...
Doubly robust off-policy evaluation - Doubly robust off-policy evaluation estimates the expected reward of a target decision policy from data collected by another policy, combining a reward or...
Dual extended Kalman filter - A dual extended Kalman filter (dual EKF or DEKF) uses two coupled estimation processes to track both a system's changing hidden state and uncertain model...
Effective model dimensionality - Effective model dimensionality describes how many independent directions of model flexibility are meaningfully determined or used under a specified dataset...
Empirical Bayes - Empirical Bayes is an approach that estimates aspects of a Bayesian analysis, commonly the prior distribution or its hyperparameters, from observed data.
Entropically regularized optimal transport - Entropically regularized optimal transport finds a mass-transfer plan that balances low transport cost with a preference for a more spread-out plan.
Entropy minimization in semisupervised learning - Entropy minimization in semisupervised learning is a training approach that encourages a classifier to make concentrated, low-entropy class predictions on...
Epanechnikov kernel - The Epanechnikov kernel is a compactly supported, parabolic weighting function used in statistical smoothing, especially kernel density estimation.
Expectation conditional maximization - Expectation conditional maximization (ECM) is a variant of the expectation-maximization algorithm that replaces a difficult joint maximization step with...
Expected calibration error - Expected calibration error (ECE) is a summary measure of how closely a classifier's stated confidence matches its observed correctness.
Expected improvement - Expected improvement (EI) is a Bayesian optimization acquisition function that measures the model-predicted average amount by which evaluating a candidate...
Exponential dispersion family - An exponential dispersion family is a class of probability distributions with a common mathematical form that separates a mean-related parameter from a...
Exponential family factor analysis - Exponential family factor analysis is a latent-variable approach that explains many observed measurements using fewer hidden factors while allowing...
Extended Kalman smoother - An extended Kalman smoother estimates past hidden states of a nonlinear dynamic system using observations collected both before and after those states.
f-divergence - An f-divergence is a measure of difference between probability distributions generated by a chosen convex function f.
Flow matching - Flow matching is a generative-model training framework that learns a time-dependent vector field for transporting a simple starting distribution toward a...
Forney factor graph - A Forney factor graph is a graphical representation of a factorized function in which nodes represent factors and edges represent variables.