Module: tfp.distributions

Statistical distributions.

Classes

class AutoCompositeTensorDistribution: Base for CompositeTensor bijectors with auto-generated TypeSpecs.

class Autoregressive: Autoregressive distributions.

class BatchBroadcast: A distribution that broadcasts an underlying distribution's batch shape.

class BatchReshape: The Batch-Reshaping distribution.

class Bates: Bates distribution.

class Bernoulli: Bernoulli distribution.

class Beta: Beta distribution.

class BetaBinomial: Beta-Binomial compound distribution.

class BetaQuotient: BetaQuotient distribution.

class Binomial: Binomial distribution.

class Blockwise: Blockwise distribution.

class Categorical: Categorical distribution over integers.

class Cauchy: The Cauchy distribution with location loc and scale scale.

class Chi: Chi distribution.

class Chi2: Chi2 distribution.

class CholeskyLKJ: The CholeskyLKJ distribution on cholesky factors of correlation matrices.

class DeterminantalPointProcess: Determinantal point process (DPP) distribution.

class Deterministic: Scalar Deterministic distribution on the real line.

class Dirichlet: Dirichlet distribution.

class DirichletMultinomial: Dirichlet-Multinomial compound distribution.

class Distribution: A generic probability distribution base class.

class DoublesidedMaxwell: Double-sided Maxwell distribution.

class Empirical: Empirical distribution.

class ExpGamma: ExpGamma distribution.

class ExpInverseGamma: ExpInverseGamma distribution.

class ExpRelaxedOneHotCategorical: ExpRelaxedOneHotCategorical distribution with temperature and logits.

class Exponential: Exponential distribution.

class ExponentiallyModifiedGaussian: Exponentially modified Gaussian distribution.

class FiniteDiscrete: The finite discrete distribution.

class Gamma: Gamma distribution.

class GammaGamma: Gamma-Gamma distribution.

class GaussianProcess: Marginal distribution of a Gaussian process at finitely many points.

class GaussianProcessRegressionModel: Posterior predictive distribution in a conjugate GP regression model.

class GeneralizedExtremeValue: The scalar GeneralizedExtremeValue distribution.

class GeneralizedNormal: The Generalized Normal distribution.

class GeneralizedPareto: The Generalized Pareto distribution.

class Geometric: Geometric distribution.

class Gumbel: The scalar Gumbel distribution with location loc and scale parameters.

class HalfCauchy: Half-Cauchy distribution.

class HalfNormal: The Half Normal distribution with scale scale.

class HalfStudentT: Half-Student's t distribution.

class HiddenMarkovModel: Hidden Markov model distribution.

class Horseshoe: Horseshoe distribution.

class Independent: Independent distribution from batch of distributions.

class Inflated: A mixture of a point-mass and another distribution.

class InverseGamma: InverseGamma distribution.

class InverseGaussian: Inverse Gaussian distribution.

class JohnsonSU: Johnson's SU-distribution.

class JointDistribution: Joint distribution over one or more component distributions.

class JointDistributionCoroutine: Joint distribution parameterized by a distribution-making generator.

class JointDistributionCoroutineAutoBatched: Joint distribution parameterized by a distribution-making generator.

class JointDistributionNamed: Joint distribution parameterized by named distribution-making functions.

class JointDistributionNamedAutoBatched: Joint distribution parameterized by named distribution-making functions.

class JointDistributionSequential: Joint distribution parameterized by distribution-making functions.

class JointDistributionSequentialAutoBatched: Joint distribution parameterized by distribution-making functions.

class Kumaraswamy: Kumaraswamy distribution.

class LKJ: The LKJ distribution on correlation matrices.

class LambertWDistribution: Implements a general heavy-tail Lambert W x F distribution.

class LambertWNormal: Implements a location-scale heavy-tail Lambert W x Normal distribution.

class Laplace: The Laplace distribution with location loc and scale parameters.

class LinearGaussianStateSpaceModel: Observation distribution from a linear Gaussian state space model.

class LogLogistic: The log-logistic distribution.

class LogNormal: The log-normal distribution.

class Logistic: The Logistic distribution with location loc and scale parameters.

class LogitNormal: The logit-normal distribution.

class MarkovChain: Distribution of a sequence generated by a memoryless process.

class Masked: A distribution that masks invalid underlying distributions.

class MatrixNormalLinearOperator: The Matrix Normal distribution on n x p matrices.

class MatrixTLinearOperator: The Matrix T distribution on n x p matrices.

class Mixture: Mixture distribution.

class MixtureSameFamily: Mixture (same-family) distribution.

class Moyal: The Moyal distribution with location loc and scale parameters.

class Multinomial: Multinomial distribution.

class MultivariateNormalDiag: The multivariate normal distribution on R^k.

class MultivariateNormalDiagPlusLowRank: The multivariate normal distribution on R^k.

class MultivariateNormalDiagPlusLowRankCovariance: The multivariate normal distribution on R^k.

class MultivariateNormalFullCovariance: The multivariate normal distribution on R^k.

class MultivariateNormalLinearOperator: The multivariate normal distribution on R^k.

class MultivariateNormalTriL: The multivariate normal distribution on R^k.

class MultivariateStudentTLinearOperator: The [Multivariate Student's t-distribution](

class NegativeBinomial: NegativeBinomial distribution.

class NoncentralChi2: Noncentral Chi2 distribution.

class Normal: The Normal distribution with location loc and scale parameters.

class NormalInverseGaussian: Normal Inverse Gaussian distribution.

class OneHotCategorical: OneHotCategorical distribution.

class OrderedLogistic: Ordered logistic distribution.

class PERT: Modified PERT distribution for modeling expert predictions.

class Pareto: Pareto distribution.

class PixelCNN: The Pixel CNN++ distribution.

class PlackettLuce: Plackett-Luce distribution over permutations.

class Poisson: Poisson distribution.

class PoissonLogNormalQuadratureCompound: PoissonLogNormalQuadratureCompound distribution.

class PowerSpherical: The Power Spherical distribution over unit vectors on S^{n-1}.

class ProbitBernoulli: ProbitBernoulli distribution.

class QuantizedDistribution: Distribution representing the quantization Y = ceiling(X).

class RegisterKL: Decorator to register a KL divergence implementation function.

class RelaxedBernoulli: RelaxedBernoulli distribution with temperature and logits parameters.

class RelaxedOneHotCategorical: RelaxedOneHotCategorical distribution with temperature and logits.

class ReparameterizationType: Instances of this class represent how sampling is reparameterized.

class Sample: Distribution over IID samples of a given shape.

class SigmoidBeta: SigmoidBeta Distribution.

class SinhArcsinh: The SinhArcsinh transformation of a distribution on (-inf, inf).

class Skellam: Skellam distribution.

class SphericalUniform: The uniform distribution over unit vectors on S^{n-1}.

class StoppingRatioLogistic: Stopping ratio logistic distribution.

class StudentT: Student's t-distribution.

class StudentTProcess: Marginal distribution of a Student's T process at finitely many points.

class StudentTProcessRegressionModel: StudentTProcessRegressionModel.

class TransformedDistribution: A Transformed Distribution.

class Triangular: Triangular distribution with low, high and peak parameters.

class TruncatedCauchy: The Truncated Cauchy distribution.

class TruncatedNormal: The Truncated Normal distribution.

class TwoPieceNormal: The Two-Piece Normal distribution.

class TwoPieceStudentT: The Two-Piece Student's t-distribution.

class Uniform: Uniform distribution with low and high parameters.

class VariationalGaussianProcess: Posterior predictive of a variational Gaussian process.

class VectorDeterministic: Vector Deterministic distribution on R^k.

class VonMises: The von Mises distribution over angles.

class VonMisesFisher: The von Mises-Fisher distribution over unit vectors on S^{n-1}.

class Weibull: The Weibull distribution with 'concentration' and scale parameters.

class WishartLinearOperator: The matrix Wishart distribution on positive definite matrices.

class WishartTriL: The matrix Wishart distribution parameterized with Cholesky factors.

class ZeroInflatedNegativeBinomial: A mixture of a point-mass and another distribution.

class Zipf: Zipf distribution.

Functions

independent_joint_distribution_from_structure(...): Turns a (potentially nested) structure of dists into a single dist.

kl_divergence(...): Get the KL-divergence KL(distribution_a || distribution_b).

mvn_conjugate_linear_update(...): Computes a conjugate normal posterior for a Bayesian linear regression.

normal_conjugates_known_scale_posterior(...): Posterior Normal distribution with conjugate prior on the mean.

normal_conjugates_known_scale_predictive(...): Posterior predictive Normal distribution w. conjugate prior on the mean.

quadrature_scheme_lognormal_gauss_hermite(...): Use Gauss-Hermite quadrature to form quadrature on positive-reals.

quadrature_scheme_lognormal_quantiles(...): Use LogNormal quantiles to form quadrature on positive-reals.

FULLY_REPARAMETERIZED Instance of tfp.distributions.ReparameterizationType
NOT_REPARAMETERIZED Instance of tfp.distributions.ReparameterizationType