Releases: tensorflow/probability
TensorFlow Probability 0.24.0
Release notes
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.)
Change notes
-
TensorFlow Probability now supports Python 3.12.
- But note that many parts of
tfp.layers
andtfp.experimental.nn
will raise errors because of a TensorFlow + wrapt bug (see tensorflow/tensorflow#60687 ), which can be worked around by setting the environment variableWRAPT_DISABLE_EXTENSIONS=true
.
- But note that many parts of
-
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 .
Huge thanks to all the contributors to this release!
- Alessandro Slamitz
- Christopher Suter
- Colin Carroll
- Emily Fertig
- Gareth Williams
- Jacob Burnim
- Jake VanderPlas
- Matthew Feickert
- Pavel Sountsov
- Richard Levasseur
- Srinivas Vasudevan
- Thomas Colthurst
- Urs Köster
TensorFlow Probability 0.23
Release notes
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 .
Change notes
[coming soon]
Huge thanks to all the contributors to this release!
- Christopher Suter
- Colin Carroll
- Jacob Burnim
- Juan Martinez
- Sergei Lebedev
- Sophia Gu
- Srinivas Vasudevan
TensorFlow Probability 0.22.1
Release notes
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 .
Change notes
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.
Huge thanks to all the contributors to this release!
- Brian Patton
- Colin Carroll
- Du Phan
- Emily Fertig
- Fiona Lang
- Frederik Gossen
- Gabriel Rasskin
- Haotian Chen
- Jacob Burnim
- Jake VanderPlas
- Mark McDonald
- Oskar Fernlund
- Pavel Sountsov
- Richard Levasseur
- Salman Faroz
- Sergei Lebedev
- Srinivas Vasudevan
- Thomas Colthurst
- Urs Köster
- Yu Feng
TensorFlow Probability 0.22.0
Release notes
This is the 0.22 release of TensorFlow Probability. It is tested and stable against TensorFlow 2.14.0 and JAX 0.4.16 .
Change notes
Support for Python 3.8 has been removed starting with TensorFlow Probability 0.22.0.
[Coming soon.]
Huge thanks to all the contributors to this release!
- Brian Patton
- Colin Carroll
- Du Phan
- Emily Fertig
- Fiona Lang
- Frederik Gossen
- Gabriel Rasskin
- Haotian Chen
- Jacob Burnim
- Jake VanderPlas
- Mark McDonald
- Oskar Fernlund
- Pavel Sountsov
- Richard Levasseur
- Salman Faroz
- Srinivas Vasudevan
- Thomas Colthurst
- Urs Köster
- Yu Feng
TensorFlow Probability 0.21.0
Release notes
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 .
Change notes
[no major changes]
Huge thanks to all the contributors to this release!
- bjp
- chansoo
- colcarroll
- emilyaf
- feyu
- flang
- Jacob Burnim
- jburnim
- jcater
- juanantoniomc
- Matthew Feickert
- oskarfernlund
- phawkins
- schwartzedward
- siege
- Srinivas Vasudevan
- ursk
TensorFlow Probability 0.20.0
Release notes
This is the 0.20 release of TensorFlow Probability. It is
tested and stable against TensorFlow version 2.12 and JAX 0.4.8 .
Change notes
- Add
LinearOperatorBasis
andLinearOperatorRowBlock
. - Ensure
Dirichlet
andRelaxedOneHotCategorical
transform correctly under bijectors. - Add
SphericalSpace
and use in all Spherical Distributions - Add
GeneralSpace.transform_general
- Fix guitar numpy rewrite_equivalence_test.
- BREAKING CHANGE: Ignore deprecated
always_yield_multivariante_normal
arg totfd.GaussianProcess
andtfd.GaussianProcessRegressionModel
so that event shape is always [1] for a single index point. - Create a
bayesopt
submodule of TFP experimental and add acquisition functions. - Add the
FeatureScaledWithCategorical
kernel, a PSD kernel over structures of continuous and categorical data, to TFP experimental. - [BREAKING] Remove deprecated arg BDF.use_pfor_to_compute_jacobian.
Huge thanks to all the contributors to this release!
- ashishenoy
- atondwal
- bjp
- Christopher Suter
- colcarroll
- Colin Carroll
- emilyaf
- fdtomasi
- flang
- Jacob Burnim
- jburnim
- jcater
- juanantoniomc
- langmore
- Leandro Campos
- leben
- Matthew Feickert
- mmladenov
- nkovela
- Pavel Sountsov
- phandu
- phawkins
- power
- S. Amin
- siege
- Srinivas Vasudevan
- synandi
- thomaswc
- Tirumalesh
- ujaved
- ursk
TensorFlow Probability 0.19.0
Release notes
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 .
Change notes
-
Bijectors
- Added
UnitVector
bijector to map to the unit sphere.
- Added
-
Distributions
- Added noncentral Chi2 distribution to TFP.
- Added differentiable quantile and cdf function approximation to NC2 distribution.
- Added quantiles to Student-T, Beta and SigmoidBeta, with efficient
implementations for Student-T quantile/cdf. - Allow structured index points to
GaussianProcess*
classes. - Improved efficiency of
GaussianProcess*
gradients through custom gradients
onlog_prob
.
-
Linear Algebra
- Added functions (with custom gradients) to handle Hermitian Symmetric Positive-definite matrices:
tfp.math.hspd_logdet
tfp.math.hpsd_quadratic_form_solve
andtfp.math.hpsd_quadratic_form_solvevec
tfp.math.hpsd_solve
andtfp.math.hpsd_solvevec
- Added functions (with custom gradients) to handle Hermitian Symmetric Positive-definite matrices:
-
Optimizer
- BUGFIX: Prevent Hager-Zhang linesearch from terminating early.
-
PSD Kernels
- Added support for structured inputs in PSD Kernel.
-
STS
- Added seasonality support to STS Gibbs Sampler.
-
Other
- BUGFIX: Allow jnp.bfloat16 arrays to be correctly recognized as floats.
Huge thanks to all the contributors to this release!
- Brian Patton
- Chen Qian
- Christopher Suter
- Colin Carrol
- Emily Fertig
- Francois Chollet
- Ian Langmore
- Jacob Burnim
- Jonas Eschle
- Kyle Loveless
- Leandro Campos
- Du Phan
- Pavel Sountsov
- Sebastian Nowozin
- Srinivas Vasudevan
- Thomas Colthurst
- Umer Javed
- Urs Koster
- Yash Katariya
TensorFlow Probability 0.18.0
Release notes
This is the 0.18.0 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.10 and JAX 0.3.17 .
Change notes
[coming soon]
Huge thanks to all the contributors to this release!
[coming soon]
TensorFlow Probability 0.17.0
Release notes
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 .
Change notes
-
Distributions
- Discrete distributions transform correctly when a bijector is applied.
- Fix bug in Taylor approximation of log-normalizing constant for the
ContinuousBernoulli
. - Add
TwoPieceNormal
distribution and reparameterize it's samples. - Make
IncrementLogProb
a proper tfd.Distribution. - Add quantiles to
Empirical
distribution. - Add
tfp.experimental.distributions.MultiTaskGaussianProcessRegressionModel
- Improve efficiency of
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. - Improve efficiency of
VariationalGaussianProcess
. - Add
tfd.LognNormal.experimental_from_mean_variance
.
-
Bijectors
- Fix Softfloor bijector to act as the identity at high temperature, and floor
at low temperature. - Remove
tfb.Ordered
bijector andfinite_nondiscrete
flags in Distributions.
- Fix Softfloor bijector to act as the identity at high temperature, and floor
-
Math
- Add tfp.math.betainc and gradients with respect to all parameters.
-
STS
- Several bug fixes and performance improvements to
tfp.experimental.sts_gibbs
for Gibbs sampling Bayesian structural time
series models with sparse linear regression. - Enable
tfp.experimental.sts_gibbs
under JAX
- Several bug fixes and performance improvements to
-
Experimental
- Ensemble Kalman filter is now efficient in the case of ensemble size << observation size and an "easy to invert" modeled observation covariance.
- Add a
perturbed_observations
option to
ensemble_kalman_filter_log_marginal_likelihood
. - Add Experimental support for custom JAX PRNGs.
-
Other
- Add
assertAllMeansClose
totfp.TestCase
for testing sampling code.
- Add
Huge thanks to all the contributors to this release!
- Adam Sorrenti
- Alexey Radul
- Christopher Suter
- Colin Carroll
- Du Phan
- Emily Fertig
- Fabien Hertschuh
- Faizan Muhammad
- Francois Chollet
- Ian Langmore
- Jacob Burnim
- Jake VanderPlas
- Kathy Wu
- Kristian Hartikainen
- Kyle Loveless
- Leandro Campos
- Xinle Sheila Liu
- ltsaprounis
- Matt Hoffman
- Manas Mohanty
- Max Jiang
- Pavel Sountsov
- Peter Hawkins
- Praveen Narayan
- Renu Patel
- Ryan Russell
- Scott Zhu
- Sergey Lebedev
- Sharad Vikram
- Srinivas Vasudevan
- tagoma
- Urs Koster
- Vaidotas Simkus
- Vishnuvardhan Janapati
- Yilei Yang
TensorFlow Probability 0.16.0
Release notes
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 .
Change notes
[coming soon]
Huge thanks to all the contributors to this release!
- Alexey Radul
- Ben Lee
- Billy Lamberta
- Brian Patton
- Chansoo Lee
- Christopher Suter
- Colin Carroll
- Dave Moore
- Du Phan
- Emily Fertig
- François Chollet
- Gianluigi Silvestri
- Jacob Burnim
- Jake Taylor
- Junpeng Lao
- Matthew Johnson
- Michael Weiss
- Pavel Sountsov
- Peter Hawkins
- Rebecca Chen
- Sharad Vikram
- Soo Sung
- Srinivas Vasudevan
- Urs Köster