Probabilistic reasoning and statistical analysis in TensorFlow
This is the 0.24.0 release of TensorFlow Probability. It is tested and stable against TensorFlow 2.16.1 and JAX 0.4.25 .
NOTE: In TensorFlow 2.16+, tf.keras
(and tf.initializers
, tf.losses
, and tf.optimizers
) refers to Keras 3. TensorFlow Probability is not compatible with Keras 3 -- instead TFP is continuing to use Keras 2, which is now packaged as tf-keras
and tf-keras-nightly
and is imported as tf_keras
. When using TensorFlow Probability with TensorFlow, you must explicitly install Keras 2 along with TensorFlow (or install tensorflow-probability[tf]
or tfp-nightly[tf]
to automatically install these dependencies.)
TensorFlow Probability now supports Python 3.12.
tfp.layers
and tfp.experimental.nn
will raise errors because of a TensorFlow + wrapt bug (see https://github.com/tensorflow/tensorflow/issues/60687 ), which can be worked around by setting the environment variable WRAPT_DISABLE_EXTENSIONS=true
.Added an experimental implementation of Chopin, Jacob, Papaspiliopoulos, "SMC^2: an efficient algorithm for sequential analysis of state-space models", Journal of the Royal Statistical Society Series B: Statistical Methodology 75.3 (2013). See https://github.com/tensorflow/probability/blob/v0.24.0/tensorflow_probability/python/experimental/mcmc/particle_filter.py#L766 .
Added tfp.experimental.fastgp
, a library for approximately training and evaluating Gaussian Processes in sub-O(n^3) time.
See https://github.com/tensorflow/probability/tree/r0.24/tensorflow_probability/python/experimental/fastgp .
This is the 0.23.0 release of TensorFlow Probability. It is tested and stable against TensorFlow 2.15.0 and JAX 0.4.20 .
[coming soon]
This is the 0.22.1 release of TensorFlow Probability. It is tested and stable against TensorFlow 2.14.0 and JAX 0.4.16 and 0.4.19 .
See the release note for TFP 0.22.0 at https://github.com/tensorflow/probability/releases/tag/v0.22.0 .
Fixes some NumPy deprecation warnings by no longer casting size-1 arrays to ints.
Dependency typing_extensions is no longer pinned to <4.6.0.
Support for Python 3.8 has been removed starting with TensorFlow Probability 0.22.0.
This is the 0.22 release of TensorFlow Probability. It is tested and stable against TensorFlow 2.14.0 and JAX 0.4.16 .
Support for Python 3.8 has been removed starting with TensorFlow Probability 0.22.0.
[Coming soon.]
This is the 0.21.0 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.13 and JAX 0.4.14 .
[no major changes]
This is the 0.20 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.12 and JAX 0.4.8 .
LinearOperatorBasis
and LinearOperatorRowBlock
.Dirichlet
and RelaxedOneHotCategorical
transform correctly under bijectors.SphericalSpace
and use in all Spherical DistributionsGeneralSpace.transform_general
always_yield_multivariante_normal
arg to tfd.GaussianProcess
and tfd.GaussianProcessRegressionModel
so that event shape is always [1] for a single index point.bayesopt
submodule of TFP experimental and add acquisition functions.FeatureScaledWithCategorical
kernel, a PSD kernel over structures of continuous and categorical data, to TFP experimental.This is the 0.19.0 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.11 and JAX 0.3.25 .
Bijectors
UnitVector
bijector to map to the unit sphere.Distributions
GaussianProcess*
classes.GaussianProcess*
gradients through custom gradients
on log_prob
.Linear Algebra
tfp.math.hspd_logdet
tfp.math.hpsd_quadratic_form_solve
and tfp.math.hpsd_quadratic_form_solvevec
tfp.math.hpsd_solve
and tfp.math.hpsd_solvevec
Optimizer
PSD Kernels
STS
Other
This is the 0.17.0 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.9.1 and JAX 0.3.13 .
Distributions
ContinuousBernoulli
.TwoPieceNormal
distribution and reparameterize it's samples.IncrementLogProb
a proper tfd.Distribution.Empirical
distribution.tfp.experimental.distributions.MultiTaskGaussianProcessRegressionModel
MultiTaskGaussian
Processes in the presence of
observation noise: Reduce complexity from O((NT)^3) to O(N^3 + T^3) where N
is the number of data points and T is the number of tasks.VariationalGaussianProcess
.tfd.LognNormal.experimental_from_mean_variance
.Bijectors
tfb.Ordered
bijector and finite_nondiscrete
flags in Distributions.Math
STS
tfp.experimental.sts_gibbs
for Gibbs sampling Bayesian structural time
series models with sparse linear regression.tfp.experimental.sts_gibbs
under JAXExperimental
perturbed_observations
option to
ensemble_kalman_filter_log_marginal_likelihood
.Other
assertAllMeansClose
to tfp.TestCase
for testing sampling code.This is the 0.16.0 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.8.0 and JAX 0.3.0 .
[coming soon]