stats (pmrf.stats)

Public stats modules and their common entry points.

Modules

bijectors	Bijectors for transforming parameters.
covariance_kernels	Covariance kernels for Gaussian processes.
discrepancy_models	Discrepancy modeling between an RF model and actual data.
distributions	Probability distribution classes and factories.
likelihoods	Likelihood models for statistical fitting.
linearization	The linearisation of a fit at its MAP, and the linearised posterior covariance.
noise_models	Measurement noise models for likelihood functions.

Classes

AbstractBijector()	Differentiable bijection that knows to compute its Jacobian determinant.
AbstractCovarianceKernel(*[, name, metadata])	Abstract base class for covariance kernel functions.
AbstractDiscrepancyModel(*[, name, metadata])	Abstract base class for discrepancy models.
AbstractDistribution()	Base class for all distreqx distributions.
AbstractLikelihood(*[, name, metadata])	Abstract base class for likelihood models.
AbstractNoiseModel(*[, name, metadata])	Abstract base class for likelihood noise models.
AutoCrossKernel(auto, cross, num_outputs, *)	Kernel that routes between a auto-correlation and cross-correlation kernels.
AutoCrossNoise(auto, cross[, port_axes, ...])	Auto and cross term noise model.
Chain(bijectors)	Composition of a sequence of bijectors into a single bijector.
ConstantKernel(variance, *[, name, metadata])	Kernel that returns a constant variance.
CosineKernel(period, *[, name, metadata])	Cosine kernel.
DiagLinear(diag)	Linear bijector with a diagonal weight matrix.
Exp([_is_constant_jacobian, ...])	Exponential bijector: y = exp(x).
Gamma(concentration, rate)	Gamma distribution with parameters concentration and rate.
GaussianLikelihood(noise, *[, name, metadata])	Gaussian likelihood with independent noise.
GaussianProcess(kernel[, jitter, name, metadata])	Gaussian process discrepancy model with a covariance kernel.
Identity([_is_constant_jacobian, ...])	Identity bijector: y = x.
Inverse(bijector)	Inverted version of a given bijector.
Joint(distributions)	Joint distribution over a PyTree of statistically independent distributions.
Leafwise(bijectors)	Applies a pytree of bijectors to a pytree of inputs.
Linearization(J, residual, chol, F, names, ...)	The linearisation of one fit at a model.
LogNormal(loc, scale)	LogNormal distribution parameterized by loc and scale of the underlying Normal.
Matern32Kernel(lengthscale, *[, name, metadata])	Matérn kernel with nu=3/2.
Matern52Kernel(lengthscale, *[, name, metadata])	Matérn kernel with nu=5/2.
Normal(loc, scale)	Normal distribution with location loc and scale parameters.
PeriodicKernel(period, lengthscale, *[, ...])	Periodic (Exp-Sine-Squared) kernel.
Permute(permutation)	Permutation bijector that reorders the elements of a 1D event.
ProductKernel(k1, k2, *[, name, metadata])	Kernel representing the product of two kernels.
R2ToComplex([_is_constant_jacobian, ...])	Maps a real array of shape (..., 2) to a complex array of shape (...).
RBFKernel(lengthscale, *[, name, metadata])	Radial Basis Function (Squared Exponential) kernel.
ScalarAffine(shift[, scale, log_scale])	An affine bijector that acts elementwise.
SharedIndependentKernel(base_kernel[, ...])	Shares a base kernel across trailing independent batch axes (e.g. the real and imaginary parts), so that every element on those axes uses the same hyperparameters.
Shift(shift)	Bijector that translates its input elementwise.
Sigmoid()	A bijector that computes the logistic sigmoid.
Softplus([_is_constant_jacobian, ...])	Transforms the real line to the positive domain using softplus y = log(1 + exp(x)).
SumKernel(k1, k2, *[, name, metadata])	Kernel representing the sum of two kernels.
Tanh()	A bijector that computes the hyperbolic tangent.
Transformed(distribution, bijector)	Distribution of a random variable transformed by a bijective function.
Transpose(permutation)	A bijector that transposes the dimensions of the input array.
TriangularLinear(matrix[, is_lower])	A linear bijector whose weight matrix is triangular.
TruncatedNormal(loc, scale, low, high)	Truncated Normal distribution with loc, scale, low, and high parameters.
Uniform(low, high)	Uniform distribution with low and high parameters.
WhiteNoiseKernel(variance, *[, name, metadata])	Kernel representing independent Gaussian noise.
ZeroKernel(*[, name, metadata])	Kernel that always evaluates to zero.

Functions

CenteredUniform(center, half_width)	Create a Uniform distribution defined by center and width.
RelativeNormal(mean, pct_std)	Create a Normal distribution defined by relative standard deviation.
RelativeTruncatedNormal(mean, pct_std[, ...])	Create a symmetric Truncated Normal distribution defined by relative standard deviation and truncated at a specified number of standard deviations from the mean.
cross_gram(kernel, x1, x2)	Build the cross-Gram matrix of a kernel between two sets of inputs.
gram(kernel, x, *[, jitter])	Build the Gram (covariance) matrix of a kernel evaluated at a set of inputs.
posterior_covariance(linearizations, model)	The linearised posterior covariance of a model's free parameters.
truncate(dist, new_lower, new_upper)	Attempts to return a truncated version of the distribution.