Module: tfp.experimental.fastgp.fast_gp

Fast likelihoods etc. for Gaussian Processes.

View aliases

Main aliases

`tfp.experimental.fastgp.fast_mtgp.fast_gp`

It's recommended to use GaussianProcess in float64 mode only.

Modules

distribution module: Base classes for probability distributions.

fast_log_det module: Functions for quickly computing approximate log det of a big PSD matrix.

gaussian_process_regression_model module: The GaussianProcessRegressionModel distribution class.

mbcg module: Modified Batched Conjugate Gradients (mBCG) for JAX.

preconditioners module: Library of popular matrix preconditioners.

softplus module: Softplus bijector.

Classes

class Array: Array base class for JAX

class GaussianProcess: Fast, JAX-only implementation of a GP distribution class.

class GaussianProcessConfig: Configuration for distributions in the FastGP family.

Functions

yt_inv_y(...): Compute y^t (kernel)^(-1) y.

yt_inv_y_jvp(...): Jacobian-Vector product for yt_inv_y.

Other Members
LOG_TWO_PI	1.8378770664093453