TensorFlow的概率方法
TensorFlow的概率方法This is a patch release for compatibility with CloudPickle >= 1.3. It is tested and stable against TensorFlow version 2.3.0.
Assets
2
Release notes
This is the 0.11 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.3.0.
Change notes
Links point to examples in the TFP 0.11.0 release Colab.

Distributions
 Support automatic vectorization in
JointDistribution*AutoBatched
instances.  Reproducible sampling, even in Eager.
 Add
Weibull
distribution.  Add
TruncatedCauchy
distribution.  Add
SphericalUniform
distribution.  Add
PowerSpherical
distribution.  Add
LogLogistic
distribution.  Add
Bates
distribution.  Add
GeneralizedNormal
distribution.  Add
JohnsonSU
distribution.  Add
ContinuousBernoulli
distribution.  Simplify
MultivariateNormalDiagPlusLowRank
and make it tapesafer; remove deprecation.  Added
KL(PowerSpherical  VonMisesFisher)
 Adds
KL(PowerSpherical  UniformSpherical)
,PowerSpherical.entropy
andSphericalUniform.entropy
 Fix gradient for
Gamma
samples with respect torate
parameter.  Increase accuracy of default
Distribution.{log_}survival_function
iflog_cdf
is implemented butcdf
is not.  More accurate log_probs and entropies across many
Distribution
s that were subtracting lgammas under the hood.  Fix
Multinomial
log_prob
when classes have zero probability.  Improve performance of
Multinomial
sampler whentotal_count
is high.  More accurate
Binomial
sampling and log_prob for large counts and small probabilities. Binomial
will no longer emit samples below 0 or abovetotal_count
. Add
nan
handling forBates
log_prob
andcdf
.  Allow named arguments in
JointDistribution*.sample()
.
 Support automatic vectorization in

Bijectors:
 Add the
Split
bijector.  Add
GompertzCDF
and ShiftedGompertzCDF bijectors  Add
Sinh
bijector. Scale
bijector can take inlog_scale
parameter.Blockwise
now supports size changing bijectors. Allow using conditioning inputs in
AutoregressiveNetwork
.  Move bijector caching logic to its own library.
 Add the

MCMC:
tfp.mcmc
now supports stateless sampling.tfp.mcmc.sample_chain(..., seed=(1,2))
is expected to always return the same results (within a release), and is deterministic (provided the underlying kernel is deterministic). Better static shape inference for MetropolisHastings kernels with partiallyspecified shapes.
TransformedTransitionKernel
nests properly with itself and other wrapper kernels. Prettyprinting MCMC kernel results.

Structured time series:
 Automatically constrain STS inference when weights have constrained support.

Math:
 Add
tfp.math.bessel_iv_ratio
for ratios of modified bessel functions of the first kind. round_exponential_bump_function
added totfp.math
. Support dynamic
num_steps
and custom convergence_criteria intfp.math.minimize
.  Add
tfp.math.log_cosh
.  Define more accurate
lbeta
andlog_gamma_difference
.
 Add

Jax/Numpy substrates:
 TFP runs on JAX!
 Expose
MaskedAutogregressiveFlow
to Numpy and JAX.

Experimental:
 Add experimental Sequential Monte Carlo sample driver.
 Add experimental tools for estimating parameters of sequential models using iterated filtering.
 Use
Distribution
s asCompositeTensor
s.  Inference Gym: Add logistic regression.
 Add support for convergence criteria in
tfp.vi.fit_surrogate_posterior
.

Other:
 Added
tfp.random.split_seed
for stateless sampling. Movedtfp.math.random_{rademacher,rayleigh}
totfp.random.{rademacher,rayleigh}
.  Possibly breaking change:
SeedStream
seed
argument may not be aTensor
.
 Added
Huge thanks to all the contributors to this release!
 Alexey Radul
 anatoly
 Anudhyan Boral
 Ben Lee
 Brian Patton
 Christopher Suter
 Colin Carroll
 Cristi Cobzarenco
 Dan Moldovan
 Dave Moore
 David Kao
 Emily Fertig
 erdembanak
 Eugene Brevdo
 Fearghus Robert Keeble
 Frank Dellaert
 Gabriel Loaiza
 Gregory Flamich
 Ian Langmore
 Iqrar Agalosi Nureyza
 Jacob Burnim
 jeffpollock9
 jekbradbury
 Jimmy Yao
 johannespitz
 Joshua V. Dillon
 Junpeng Lao
 Kate Lin
 Ken Franko
 luke199629
 Mark Daoust
 Markus Kaiser
 Martin Jul
 Matthew Feickert
 Maxim Polunin
 Nicolas
 npfp
 Pavel Sountsov
 Peng YU
 Rebecca Chen
 Rif A. Saurous
 Ru Pei
 Sayam753
 Sharad Vikram
 Srinivas Vasudevan
 summeryue
 Tom Charnock
 Tres Popp
 Wataru Hashimoto
 Yash Katariya
 Zichun Ye
Assets
2
emilyfertig released this
This is RC1 of the TensorFlow Probability 0.11 release. It is tested against TensorFlow 2.3.0rc2.
Assets
2
This is a patch release to pin the CloudPickle version to 1.3 to address #991 . It is tested and stable against TensorFlow version 2.2.0.
Assets
2
Release notes
This is the 0.10 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.2.0.
Change notes

Distributions
 BetaBinomial distribution.
 Add new
AutoBatched
joint distribution variants that treat a joint sample as a single probabilistic event.  XLAable Python TF Gamma sampler.
 XLAable binomial sampler. Replaces the existing sampler, which implements binomial using onehot categoricals via multinomial, with a batched rejection sampler. The new sampler is 46 times slower for very small problems, but an unbounded amount faster on large problems, since it removes a linear dependency on
total_count
. Additionally, since the previous solver required memory proportional to total_count*num_samples, many problems which OOM'd before are now feasible.  Enable use of joint bijectors in TransformedDistribution.
 Remove unused
get_logits_and_probs
from internal/distribution_util.  Batched rejection sampling utilities.
 Update batched_rejection_sampler to use prefer_static.shape to handle possiblydynamic shape.

Bijectors
 Add Lambert W transform bijectors.

MCMC
 EllipticalSliceSampler in tfp.experimental.mcmc
 Add crosschain ESS, following Vehtari et al. 2019.

Optimizer
 Add convergence criteria for optimizations.

Stats
 Add
tfp.stats.expected_calibration_error_quantiles
.
 Add

Math
 Add a 'special' module to tfp.math  a TF version of scipy.special.
 Add
scan_associative
function, implementing parallel prefix scan of tensors with a userprovided binary operation.

Breaking change: Removed a number of functions, methods, and classes that were deprecated in TensorFlow Probability 0.9.0 or earlier.
 Removed deprecated tfb.Weibull  use tfb.WeibullCDF.
 Remove VectorLaplaceLinearOperator
 Remove deprecated method
tfp.sts.build_factored_variational_loss
.  Remove deprecated tfb.Kumaraswamy  use tfb.Invert(tfb.KumaraswamyCDF).
 Remove deprecated tfd.VectorSinhArcsinhDiag, tfd.VectorLaplaceDiag.
 Remove deprecated
tfb.Gumbel
 usetfb.GumbelCDF
.

Other
 Python 3.8 compatibility.
 Raise minimum required TF version to 2.1.
 TensorFlow now requires gast version 0.3.2 and is no longer compatible with 0.2.2.
 Moving TF Session C++ to Python code and functionality from swig to pybind11.
 Update TFP examples to Python 3.
Huge thanks to all the contributors to this release!
 Alexander Ivanov
 Alexey Radul
 Amanda
 Amelio VazquezReina
 Amit Patankar
 Anudhyan Boral
 Artem Belevich
 Brian Patton
 Christopher Suter
 Colin Carroll
 Dan Moldovan
 Dave Moore
 Demetri Pananos
 Dmitrii Kochkov
 Emily Fertig
 gameshamilton
 Georg M. Goerg
 Ian Langmore
 Jacob Burnim
 jeffpollock9
 Joshua V. Dillon
 Junpeng Lao
 kovak1
 Kristian Hartikainen
 Liam
 Martin Jul
 Matt Hoffman
 nbro
 Olli Huotari
 Pavel Sountsov
 Pyrsos
 Rif A. Saurous
 Rushabh Vasani
 Sayam753
 Sharad Vikram
 Spyros
 Srinivas Vasudevan
 Taylor Robie
 Xiaojing Wang
 Zichun Ye
Assets
2
emilyfertig released this
This is RC1 of the TensorFlow Probability 0.10 release. It is tested against TensorFlow 2.2.0rc4.
Assets
2
emilyfertig released this
This is the RC0 release candidate of the Tensorflow Probability 0.10 release. It is tested against Tensorflow 2.2.0rc3.
Assets
2
Release notes
This is the 0.9 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.1.0.
NOTE: The 0.9 releases of TensorFlow Probability will be the last to support Python 2. Future versions of TensorFlow Probability will require Python 3.5 or later.
Change notes

Distributions
 Add Pixel CNN++ distribution.
 Breaking change: Remove deprecated behavior of
Poisson.rate
andPoisson.log_rate
.  Breaking change: Remove deprecated behavior of
logits
,probs
properties.  Add
_default_event_space_bijector
to distributions.  Add validation that samples are within the support of the distribution.
 Support positional and keyword args to
JointDistribution.prob
andJointDistribution.log_prob
.  Support
OrderedDict
dtype inJointDistributionNamed
. tfd.BatchReshape
is tapesafe More accurate survival function and CDF for the generalized Pareto distribution.
 Added PlackettLuce distribution over permutations.
 Fix longstanding bug with
cdf
,survival_function
, andquantile
forTransformedDistribution
s having decreasing bijectors.  Export the DoubleMaxwell distribution.
 Add method for analytic Bayesian linear regression with LinearOperators.

Bijectors
 Breaking change: Scalar bijectors must implement
_is_increasing
if usingcdf
/survival_function
/quantile
onTransformedDistribution
. This supports resolution of a longstanding bug, e.g.tfb.Scale(scale=1.)(tfd.HalfNormal(0,1)).cdf
was incorrect.  Deprecate tfb.masked_autoregressive_default_template.
 Fixed inverse numerical stability bug in
tfb.Softfloor
 Tapesafe Reshape bijector.
 Breaking change: Scalar bijectors must implement

MCMC
 Optimize tfp.mcmc.ReplicaExchangeMonteCarlo by replacing TF control flow and
 ReplicaExchangeMC now can trace exchange proposals/acceptances.
 Correct implementation of log_accept_ratio in NUTS
 Return noncumulated leapfrogs_taken in nuts kernel_result.
 Make unrolled NUTS reproducible.
 Bug fix of Generalized Uturn in NUTS.
 Reduce NUTS test flakiness.
 Fix convergence test for NUTS.
 Switch back to original U turn criteria in Hoffman & Gelman 2014.
 Make autobatched NUTS reproducible.

STS
 Update example "Structural Time Series Modeling Case Studies" to TF2.0 API.
 Add fast path for sampling STS LocalLevel models.
 Support posterior sampling in linear Gaussian state space models.
 Add a fast path for Kalman smoothing with scalar latents.
 Add option to disallow drift in STS Seasonal models.

Breaking change: Removed a number of functions, methods, and classes that were deprecated in TensorFlow Probability 0.8.0 or earlier.
 Remove deprecated
trainable_distributions_lib
.  Remove deprecated property Dirichlet.total_concentration.
 Remove deprecated
tfb.AutoregressiveLayer
 usetfb.AutoregressiveNetwork
.  Remove deprecated
tfp.distributions.*
methods.  Remove deprecated
tfp.distributions.moving_mean_variance
.  Remove two deprecated
tfp.vi
functions.  Remove deprecated
tfp.distributions.SeedStream
 usetfp.util.SeedStream
.  Remove deprecated properties of
tfd.Categorical
.
 Remove deprecated

Other
 Add
make_rank_polymorphic
utility, which lifts a callable to a vectorized callable.  DormandPrince solver supports nested structures. Implemented adjoint sensitivity method for DormandPrince solver gradients.
 Run Travis tests against latest tfestimatornightly.
 Supporting gast 0.3 +
 Add
tfp.vi.build_factored_surrogate_posterior
utility for automatic blackbox variational inference.
 Add
Huge thanks to all the contributors to this release!
 Aditya Grover
 Alexey Radul
 Anudhyan Boral
 Arthur Lui
 Billy Lamberta
 Brian Patton
 Christopher Suter
 Colemak
 Dan Moldovan
 Dave Moore
 Dmitrii Kochkov
 Edward Loper
 Emily Fertig
 Ian Langmore
 Jacob Burnim
 Joshua V. Dillon
 Junpeng Lao
 Katherine Wu
 Kibeom Kim
 Kristian Hartikainen
 Mark Daoust
 Pavel Sountsov
 Peter Hawkins
 refractionray
 RJ SkerryRyan
 Sanket Kamthe
 Sergei Lebedev
 Sharad Vikram
 Srinivas Vasudevan
 Yanhua Sun
 Yash Katariya
 Zachary Nado
Assets
2
Release notes
This is the 0.8 release of TensorFlow Probability. It is tested and stable against TensorFlow version 2.0.0 and 1.15.0rc1.
Change notes

GPUfriendly "unrolled" NUTS:
tfp.mcmc.NoUTurnSampler
 Opensource the unrolled implementation of the No UTurn Sampler.
 Switch back to original U turn criteria in Hoffman & Gelman 2014.
 Bug fix in Unrolled NUTS to make sure it does not lose shape for event_shape=1.
 Bug fix of U turn check in Unrolled NUTS at the tree extension.
 Refactor U turn check in Unrolled NUTS.
 Fix dynamic shape bug in Unrolled NUTS.
 Move NUTS unrolled into mcmc, with additional clean up.
 Make sure the unrolled NUTS sampler handle scalar target_log_probs correctly.
 Change implementation of check U turn to using a tf.while_loop in unrolled NUTS.
 Implement multinomial sampling across tree (instead of Slice sampling) in unrolled NUTS.
 Expose additional diagnostics in
previous_kernel_results
in unrolled NUTS so that it works with*_step_size_adaptation
.

MCMC
 Modify the shape handling in DualAveragingStepSizeAdaptation so that it works with nonscalar event_shape.
 support structured samples in
tfp.monte_carlo.expectation
.  Minor fix for docstring example in leapfrog_integrator

VI
 Add utilities for fitting variational distributions.
 Improve Csiszar divergence support for joint variational distributions.
 ensure that joint distributions are correctly recognized as reparameterizable by
monte_carlo_csiszar_f_divergence
.  Rename
monte_carlo_csiszar_f_divergence
tomonte_carlo_variational_loss
.  Refactor tfp.vi.csiszar_vimco_helper to expose useful leaveoneout statistical tools.

Distributions
 Added
tfp.distributions.GeneralizedPareto
 Multinomial and DirichletMultinomial samplers are now reproducible.
 HMM samples are now reproducible.
 Cleaning up unneeded conversion to tensor in quantile().
 Added support for dynamic
num_steps
inHiddenMarkovModel
 Added implementation of quantile() for exponential distributions.
 Fix entropy of Categorical distribution when logits contains inf.
 Annotate floatvalued Deterministic distributions as reparameterized.
 Establish patterns which ensure that TFP objects are "GradientTape Safe."
 "GradientTapesafe" distributions: FiniteDiscrete, VonMises, Binomial, Dirichlet, Multinomial, DirichletMultinomial, Categorical, Deterministic
 Add
tfp.util.DeferredTensor
to delay Tensor operations ontf.Variable
s (also works fortf.Tensor
s).  Add
probs_parameter
,logits_parameter
member functions to Categoricallike distributions. In the future users should use these new functions rather thanprobs
/logits
properties because the properties might beNone
if that's how the distribution was parameterized.
 Added

Bijectors
 Add
log_scale
parameter to AffineScalar bijector.  Added
tfp.bijectors.RationalQuadraticSpline
.  Add SoftFloor bijector. (Note: Known inverse bug WIP.)
 Allow using an arbitrary bijector in RealNVP for the coupling.
 Allow using an arbitrary bijector in MaskedAutoregressiveFlow for the coupling.
 Add

Experimental autobatching system:
tfp.experimental.auto_batching
 Opensource the programcounterbased autobatching system.
 Added tfp.experimental.auto_batching, an experimental system to recover batch parallelism across recursive function invocations.
 Autobatched NUTS supports batching across consecutive trajectories.
 Add support for field references to autobatching.
 Increase the amount of Python syntax that "just works" in autobatched functions.
 poppush fusion optimization in the autobatching system (also recently did tailcall optimization but forgot to add a relnote).
 Opensource the autobatched implementation of the No UTurn Sampler.

STS
 Support TF2/Eagermode fitting of STS models, and deprecate
build_factored_variational_loss
.  Use dual averaging step size adaptation for STS HMC fitting.
 Add support for imputing missing values in structural time series models.
 Standardize parameter scales during STS inference.
 Support TF2/Eagermode fitting of STS models, and deprecate

Layers
 Add WeightNorm layer wrapper.
 Fix gradients flowing through variables in the old style variational layers.
tf.keras.model.save_model
andmodel.save
now defaults to saving a TensorFlow SavedModel.

Stats/Math
 Add calibration metrics to tfp.stats.
 Add output_gradients argument to value_and_gradient.
 Add Geyer initial positive sequence truncation criterion to tfp.mcmc.effective_sample_size.
 Resolve shape inconsistencies in PSDKernels API.
 Support dynamicshaped results in
tfp.math.minimize
.  ODE: Implement the Adjoint Method for gradients with respect to the initial state.
Huge thanks to all the contributors to this release!
 Alexey Radul
 Anudhyan Boral
 Arthur Lui
 Brian Patton
 Christopher Suter
 Colin Carroll
 Dan Moldovan
 Dave Moore
 Edward Loper
 Emily Fertig
 Gaurav Jain
 Ian Langmore
 Igor Ganichev
 Jacob Burnim
 Jeff Pollock
 Joshua V. Dillon
 Junpeng Lao
 Katherine Wu
 Mark Daoust
 Matthieu Coquet
 Parsiad Azimzadeh
 Pavel Sountsov
 Pavithra Vijay
 PJ Trainor
 prabhu prakash kagitha
 prakashkagitha
 Reed WandermanMilne
 refractionray
 Rif A. Saurous
 RJ SkerryRyan
 Saurabh Saxena
 Sharad Vikram
 Sigrid Keydana
 skeydan
 Srinivas Vasudevan
 Yash Katariya
 Zachary Nado
Assets
2
This is the RC0 release candidate of the TensorFlow Probability 0.8 release.
It is tested against TensorFlow 2.0.0rc0
Assets
2
Release notes
This is the 0.7 release of TensorFlow Probability. It is tested and stable against TensorFlow version 1.14.0.
Change notes
 Internal optimizations to HMC leapfrog integrator.
 Add FeatureTransformed, FeatureScaled, and KumaraswamyTransformed PSD kernels
 Added tfp.debugging.benchmarking.benchmark_tf_function.
 Added optional masking of observations for
hidden_markov_model
methodsposterior_marginals
andposterior_mode
.  Fixed evaluation order of distributions within
JointDistributionNamed
 Rename tfb.AutoregressiveLayer to tfb.AutoregressiveNetwork.
 Support kernel and bias constraints/regularizers/initializers in tfb.AutoregressiveLayer.
 Created Backward Difference Formula (BDF) solver for stiff ODEs.
 Update Cumsum bijector.
 Add distribution layer for masked autoregressive flow in Keras.
 Shorten
repr
,str
Distribution strings by using"?"
instead of"<unknown>"
to representNone
.  Implement FiniteDiscrete distribution
 Add Cumsum bijector.
 Make Seasonal STS more flexible to handle none constant num_steps_per_season for each season.
 In tfb.BatchNormalization, use keras layer over compat.v1 layer.
 Forward kwargs in MaskedAutoregressiveFlow.
 Added tfp.math.pivoted_cholesky for low rank preconditioning.
 Add
tfp.distributions.JointDistributionCoroutine
for specifying simple directed graphical models via Python generators.  Complete the example notebook demonstrating multilevel modeling using TFP.
 Remove default
None
initializations for Beta and LogNormal parameters.  Bug fix in init method of Rational quadratic kernel
 Add Binomial.sample method.
 Add SparseLinearRegression structural time series component.
 Remove TFP support of KL Divergence calculation of tf.compat.v1.distributions which have been deprecated for 6 months.
 Added
tfp.math.cholesky_concat
(adds columns to a cholesky decomposition)  Introduce SchurComplement PSD Kernel
 Add EllipticalSliceSampler as an experimental MCMC kernel.
 Remove intercepting/reuse of variables created within DistributionLambda.
 Support missing observations in structural time series models.
 Add Keras layer for masked autoregressive flows.
 Add code block to show recommended style of using JointDistribution.
 Added example notebook demonstrating multilevel modeling.
 Correctly decorate the training block in the VI part of the JointDistribution example notebook.
 Add
tfp.distributions.Sample
for specifying plates in tfd.JointDistribution*.  Enable save/load of Keras models with DistributionLambda layers.
 Add example notebook to show how to use joint distribution sequential for smallmedian Bayesian graphical model.
 Add NaN propagation to tfp.stats.percentile.
 Add
tfp.distributions.JointDistributionSequential
for specifying simple directed graphical models.  Enable save/load of models with IndependentX or MixtureX layers.
 Extend monte_carlo_csiszar_f_divergence so it also work with JointDistribution.
 Fix typo in
value_and_gradient
docstring.  Add
SimpleStepSizeAdaptation
, deprecatestep_size_adaptation_fn
.  batch_interp_regular_nd_grid added to tfp.math
 Adds IteratedSigmoidCentered bijector to unconstrain unit simplex.
 Add option to constrain seasonal effects to zerosum in STS models, and enable by default.
 Add twosample multivariate equality in distribution.
 Fix broadcasting errors when forecasting STS models with batch shape.
 Adds batch slicing support to most distributions in tfp.distributions.
 Add tfp.layers.VariationalGaussianProcess.
 Added
posterior_mode
toHiddenMarkovModel
 Add VariationalGaussianProcess distribution.
 Adds slicing of distributions batch axes as
dist[..., :2, tf.newaxis, 3]
 Add tfp.layers.VariableLayer for making a Keras model which ignores inputs.
tfp.math.matrix_rank
. Add KL divergence between two blockwise distributions.
tf.function
decoratetfp.bijectors
. Add
Blockwise
distribution for concatenating different distribution families.  Add and begin using a utility for varying random seeds in tests when desired.
 Add twosample calibrated statistical test for equality of CDFs, incl. support for duplicate samples.
 Deprecating obsolete
moving_mean_variance
. Useassign_moving_mean_variance
and manage the variables explicitly.  Migrate Variational SGD Optimizer to TF 2.0
 Migrate SGLD Optimizer to TF 2.0
 TF2 migration
 Make all test in MCMC TF2 compatible.
 Expose HMC parameters via kernel results.
 Implement a new version of sample_chain with optional tracing.
 Make MCMC diagnostic tests Eager/TF2 compatible.
 Implement Categorical to Discrete Values bijector, which maps integer x (0<=x<K) to values[x], where values is a predefined 1D tensor with size K.
 Run dense, conv variational layer tests in eager mode.
 Add Empirical distribution to Edward2 (already exists as a TFP distribution).
 Ensure Gumbel distribution does not produce
inf
samples.  Hid tensor shapes from operators in HMM tests
 Added
Empirical
distribution  Add the
Blockwise
bijector.  Add
MixtureNormal
andMixtureLogistic
distribution layers.  Experimental support for implicit reparameterization gradients in MixtureSameFamily
 Fix parameter broadcasting in
DirichletMultinomial
.  Add
tfp.math.clip_by_value_preserve_gradient
.  Rename InverseGamma
rate
parameter toscale
, to match its semantics.  Added option 'input_output_cholesky' to LKJ distribution.
 Add a semilocal linear trend STS model component.
 Added Proximal Hessian Sparse Optimizer (a variant of NewtonRaphson).
 find_bins(x, edges, ...) added to tfp.stats.
 Disable explicit caching in masked_autoregressive in eager mode.
 Add a local level STS model component.
 Docfix: Fix constraint on valid range of reinterpreted_batch_dims for Independent.
Huge thanks to all the contributors to this release!
 Alexey Radul
 Anudhyan Boral
 axch
 Brian Patton
 cclauss
 Chikanaga Tomoyuki
 Christopher Suter
 Clive Chan
 Dave Moore
 Gaurav Jain
 harrismirza
 Harris Mirza
 Ian Langmore
 Jacob Burnim
 Janosh Riebesell
 Jeff Pollock
 Jiri Simsa
 joeyhaohao
 johndebugger
 Joshua V. Dillon
 Juan A. Navarro P?rez
 Junpeng Lao
 Matej Rizman
 Matthew O'Kelly
 MG92
 Nicola De Cao
 Parsiad Azimzadeh
 Pavel Sountsov
 Philip Pham
 PJ Trainor
 Rif A. Saurous
 Sergei Lebedev
 Sigrid Keydana
 Sophia Gu
 Srinivas Vasudevan
 ykkawana
Assets
2
This is the 0.7.0rc0 release of TensorFlow Probability. It is
tested and stable against TensorFlow version 1.14rc0 and 2.0.0alpha
Assets
2
Release notes
This is the 0.6 release of TensorFlow Probability. It is
tested and stable against TensorFlow version 1.13.1.
Change notes
 Adds tfp.positive_semidefinite_kernels.RationalQuadratic
 Support float64 in tfpl.MultivariateNormalTriL.
 Add IndependentLogistic and IndependentPoisson distribution layers.
 Add
make_value_setter
interceptor to set values of Edward2 random variables.  Implementation of Kalman Smoother, as a member function of LinearGaussianStateSpaceModel.
 Bijector caching is enabled only in one direction when executing in eager mode. May cause some performance regression in eager mode if repeatedly computing
forward(x)
orinverse(y)
with the samex
ory
value.  Handle rank0/empty event_shape in tfpl.Independent{Bernoulli,Normal}.
 Run additional tests in eager mode.
 quantiles(x, n, ...) added to tfp.stats.
 Makes tensorflow_probability compatible with Tensorflow 2.0 TensorShape indexing.
 Use scipy.special functions when testing KL divergence for Chi, Chi2.
 Add methods to create forecasts from STS models.
 Add a MixtureSameFamily distribution layer.
 Add Chi distribution.
 Fix doc typo
tfp.Distribution
>tfd.Distribution
.  Add GumbelGumbel KL divergence.
 Add HalfNormalHalfNormal KL divergence.
 Add Chi2Chi2 KL divergence unit tests.
 Add ExponentialExponential KL divergence unit tests.
 Add sampling test for NormalNormal KL divergence.
 Add an IndependentNormal distribution layer.
 Added
posterior_marginals
toHiddenMarkovModel
 Add ParetoPareto KL divergence.
 Add LinearRegression component for structural time series models.
 Add dataset ops to the graph (or create kernels in Eager execution) during the python Dataset object creation instead doing it during Iterator creation time.
 Text messages HMC benchmark.
 Add example notebook encoding a switching Poisson process as an HMM for multiple changepoint detection.
 Require
num_adaptation_steps
argument tomake_simple_step_size_update_policy
.  s/eight_hmc_schools/eight_schools_hmc/ in printed benchmark string.
 Add
tfp.layers.DistributionLambda
to enable plumbingtfd.Distribution
instances through Keras models.  Adding tfp.math.batch_interp_regular_1d_grid.
 Update description of fill_triangular to include an indepth example.
 Enable bijector/distribution composition, eg,
tfb.Exp(tfd.Normal(0,1))
.  linear and midpoint interpolation added to tfp.stats.percentile.
 Make distributions include only the bijectors they use.
 tfp.math.interp_regular_1d_grid added
 tfp.stats.correlation added (Pearson correlation).
 Update list of edward2 RVs to include recently added Distributions.
 Density of continuous Uniform distribution includes the upper endpoint.
 Add support for batched inputs in tfp.glm.fit_sparse.
 interp_regular_1d_grid added to tfp.math.
 Added HiddenMarkovModel distribution.
 Add Student's T Process.
 Optimize LinearGaussianStateSpaceModel by avoiding matrix ops when the observations are statically known to be scalar.
 stddev, cholesky added to tfp.stats.
 Add methods to fit structual time series models to data with variational inference and HMC.
 Add Expm1 bijector (Y = Exp(X)  1).
 New stats namespace. covariance and variance added to tfp.stats
 Make all available MCMC kernels compatible with TransformedTransitionKernel.
Huge thanks to all the contributors to this release!
 Adam Wood
 Alexey Radul
 Anudhyan Boral
 Ashish Saxena
 Billy Lamberta
 Brian Patton
 Christopher Suter
 Cyril Chimisov
 Dave Moore
 Eugene Zhulenev
 Griffin Tabor
 Ian Langmore
 Jacob Burnim
 Jakub Arnold
 Jiahao Yao
 Jihun
 Jiming Ye
 Joshua V. Dillon
 Juan A. Navarro Pérez
 Julius Kunze
 Julius Plenz
 Kristian Hartikainen
 Kyle Beauchamp
 Matej Rizman
 Pavel Sountsov
 Peter Roelants
 Rif A. Saurous
 Rohan Jain
 Roman Ring
 Rui Zhao
 Sergio Guadarrama
 Shuhei Iitsuka
 Shuming Hu
 Srinivas Vasudevan
 Tabor473
 ValentinMouret
 Youngwook Kim
 Yuki Nagae
Assets
2
This is the 0.6.0rc1 release candidate of TensorFlow Probability. It is tested against TensorFlow 1.13.0rc2.
Assets
2
Assets
2
This is the RC0 release candidate of the TensorFlow Probability 0.6 release.
It is tested against TensorFlow 1.13.0rc0
Assets
2
Release Notes
This is the 0.5.0 release of TensorFlow Probability. It's tested and stable against TensorFlow 1.12.
Packaging Change
As of this release, we no longer package a separate GPUspecific build. Users can select the version of TensorFlow they wish to use (CPU or GPU), and TensorFlow Probability will work with both.
As a result, we no longer explicitly list a TensorFlow dependency in our package requirements (since we can't know which version the user will want). If TFP is installed with no TensorFlow package present, or with an unsupported TensorFlow version, we will issue an ImportError
at time of import.
Distributions & Bijectors
 All
Distribution
s have been relocated fromtf.distributions
totfp.distributions
(the ones in TF are deprecated and will be deleted in TF 2.0).  Add Triangular distribution.
 Add Zipf distribution.
 Add NormalCDF Bijector.
 Add Multivariate Student's tdistribution.
 Add RationalQuadratic kernel.
Documentation & Examples
 Add example showing how to fit GLMM using Variational Inference.
 Introduce Gaussian process latent variable model colab.
 Introduce Gaussian process regression example colab
 Add notebook showcasing GLM algorithms and deriving some results about GLMs that those algorithms leverage.
Huge thanks to all the contributors to this release!
 Akshay Modi
 Alexey Radul
 Anudhyan Boral
 Ashish Saxena
 Ben Zinberg
 Billy Lamberta
 Brian Patton
 Christopher Suter
 Dave Moore
 Ian Langmore
 Joshua V. Dillon
 Kristian Hartikainen
 Malcolm Reynolds
 Pavel Sountsov
 Srinivas Vasudevan
 Xiaojing Wang
 Yifei Feng
Assets
2
This is the RC1 release candidate of the TensorFlow Probability 0.5 release.
It is tested against TensorFlow 1.12.0rc2
Assets
2
This is the RC0 release candidate of the TensorFlow Probability 0.5 release.
It is tested against TensorFlow 1.12.0rc2
TensorFlow Probability 0.3.0rc2
csuter released this
This is the rc1 release. We never actually built rc1, since we needed to cherrypick a few more things.
This release is tested against TensorFlow v1.10.0
TensorFlow Probability 0.2.0
csuter released this
This is the 0.2 release of TensorFlow Probability, our first versioned release.
It is tested against TensorFlow 1.9.0.
TensorFlow Probability 0.2.0rc0
csuter released this
This is release candidate rc0, of our 0.2 release of TensorFlow Probability.
It is tested against TensorFlow 1.9.0.
TensorFlow Probability 0.1.0rc1
csuter released this
Release 0.1.0rc1
This is release candidate rc1, of our first versioned release of TensorFlow Probability.
It is tested against TensorFlow 1.9.0rc1.
Watchers：177 
Star：3132 
Fork：824 
创建时间： 20171024 07:50:54 
最后Commits： 5天前 
许可协议：Apache2.0 
7784466
Compare
Verified
jburnim released this
Nov 11, 2020
This is RC1 of the TensorFlow Probability 0.12 release. It is tested against TensorFlow 2.4.0rc1.