Revision db9f9966c43541b85439af0ab39fe3e3444ef14b authored by Daniel Lee on 03 July 2014, 19:22:22 UTC, committed by Daniel Lee on 03 July 2014, 19:22:22 UTC
Feature/lbfgs
RELEASE-NOTES.txt
STAN C++ RELEASE NOTES
======================================================================
v.2.3.0 (18 June 2014)
======================================================================
We had a record number of user-submitted patches this go around.
Thanks to everyone!
New Features
------------
* user-defined function definitions added to Stan language
* a^b syntax for pow(a,b) (thanks to Mitzi Morris)
* reshaping functions: to_matrix(), to_vector(), to_row_vector(),
to_array_1d(), to_array_2d()
* matrix operations: quad_form_sym() (x' *Sigma * x), QR decompositions
qr_Q(), qr_R()
* densities: Gaussian processes multi_gp_log(), multi_gp(),
and alternative negative binomial parameterization neg_binomial_2()
* random number generator: multi_normal_cholesky_rng()
* sorting: sort_indices_*() for returning indexes in sorted order by
value
* added JSON parser to C++ (not exposed through interfaces yet; thanks
to Mitzi Morris)
* many fixes to I/O for data and inits to check consistency and
report errors
* removed some uses of std::cout where they don't belong
* updated parser for C++11 compatibility (thanks to Rob Goedman)
New Developer
--------------
* added Marco Inacio as core developer
Optimizations
-------------
* turned off Eigen asserts
* efficiency improvements to posterior analysis print
Documentation
-------------
* Clarified licensing policy for individual code contributions
* Huge numbers of fixes to the documentation, including many
user-contributed patches (thanks!), fixes to parallelization in
CmdStan, Windows install instructions, boundaries for Dirichlet and
Beta, removed suggestion to use floor and ceiling as indices,
vectorized many models, clarified that && doesn't short circuit,
clarified von Mises normalization, updated censoring doc (thanks
to Alexey Stukalov), negative binomial doc enhanced, new references,
new discussion of hierarchical models referencing Betancourt and
Girolami paper,
* Avraham Aadler was particularly useful in pointing out and fixing
documentation errors
Bug Fixes
------------
* fixed bug in lkj density
* fixed bug in Jacobian for corr_matrix data type
* fix cholesky_cov_matrix test code to allow use as parameter
* fixed poisson_rng, neg_binomial_rng
* allow binary operations (e.g., < and >) within range constraints
* support MS Visual Studio 2008
* fixed memory leaks in categorical sampling statement, categorical_log
function, and softmax functions
* removed many compiler warnings
* numerous bug fixes to arithmetic test code conditions and messages,
including calls from
* fixed model crashes when no parameter specified
* fixed template name conflicts for some compiler bugs (thanks Kevin
S. Van Horn)
Code Reorganizations & Updates
------------------------------
* CmdStan is now in its own repository on GitHub: stan-dev/cmdstan
* consolidate and simplify error handling across modules
* pulled functionality from CmdStan command class and PyStan and RStan
into Stan C++
* generalized some interfaces to allow std::vector as well as Eigen
for compatibility
* generalize some I/O CSV writer capabilities
* optimization output text cleaned up
* integer overflow during I/O now raises informative error messages
* const correctness for chains (thanks Kevin S. Van Horn)
v2.3.0 (16 June 2014)
======================================================================
Bug Fixes
------------
* fixed poisson_rng, neg_binomial_rng
* integer overflow now throws errors
* allow < and > within range constraints
* support MS Visual Studio 2008
* fixed bug in lkj
Features
------------
* functions added to Stan language!
* turned off eigen asserts
* CmdStan is now in its own repository
* added quad_form_sym, multi_gp_log, multi_gp,
multi_normal_cholesky_rng, to_matrix, to_vector, to_array, flatten,
qr_Q, qr_R
* added JSON parser to Stan
* a^b syntax for pow(a,b)
v2.2.0 (14 February 2014)
======================================================================
Bug Fixes
-------------
* increment_log_prob is now vectorized and compiles with vector arguments
* multinomial random number generator used the wrong size for the return value
* fixed memory leaks in auto-diff implementation
* variables can start with the prefix 'inf'
* fixed parameter output order for arrays when using optimization
Features
-------------
* suppress command line output with refresh <= 0
* added 1 to treedepth to match usual definition of treedepth
* added distance, squared_distance, diag_pre_multiply, diag_pre_multiply to Stan modeling lnaguage
* added a 'fixed_param' sampler for use with the generated quantities block
v2.0.1 (24 October 2013)
======================================================================
Bug Fixes
----------------------------------
* fixed multi_normal distribution's gradient calculations
* fixed diagnose mode from the command line to work for matrices
* typos in the manual
v2.0.0 (16 October 2013)
======================================================================
This list is incomplete. The 2.0.0 update is a huge fix, and this
list just represents what was clearly called out in pull requests.
Enhancements
----------------------------------
* all new hierarchical command-line interface
* compiler flags to build with Xcode 5 (which has too-small template-depth)
* BFGS optimization
* print variable name when initialization fails
* reserved function names (breaks backward compatibility)
* deprecate direct use of lp__ in favor of increment_log_prob()
* unfolded softmax for more efficiency, optimized and vectorized categorical
* new Cholesky factor data type
* upgraded to Boost 1.54 and Eigen 3.2.0
* added flag to suppress Jacobian adjustment in log prob (for
optimizers)
* added Rayleigh distribution
* added Bessel (and modified Bessel) functions of first and second
kind
* added Pochhammer functions (rising/falling factorials)
* completed vectorization of univariate distributions
* trapped use of "." in variable names and print error
* moved RStan into its own subproject
* rewrote writer interface for samples
* added delete method to chainables to allow exceptions in
constructors
* added sort and rank functions
* improved doc and coding for GP example models
* shuffle function signature tests for test speed
* new gradient functionality for memory allocation and cleaning
and to reduce code duplication
Bug Fixes
----------------------------------
* remove function signatures from undocumented functions
* fixed broken abs(real) signature; deprecated abs(real) in favor
of fabs(real)
* error checking for dirichlet
* fix bin/print to be row major
* suppress warnings for unused variables; cleanup truly unused ones
* fixed pow() boundary conditions with negative base, fractional
exponent
* fix model tests and error codes
* fix command-line return codes to be more compliant
* fix build parameter names to be more compliant with conventions
* fix integer vs. real problems in some RNGs
* fix print so that it prints expression values, not just names
* fix Newton optimization backtrack to eventually terminate with
failure rather than looping infinitely
* fix CSV output from command for matrices (was transposed)
* fixes to allow Stan to build under Cygwin
* fix double indexing on LHS of assignment
* fix nested expression prints to allow indexed array sizes in
declarations
* fix parameterization of gamma RNG
* reserved model's class name as variable
* added vector size test in assignment
* fixed mixture examples
* fixed rep_vector to work with integer value
* fixed parser error message
* fixed use of Boost NaN tests
* initialze local variables to NaN to prevent segfaults if used
before defined
* remove unused includes from model header
* fix signed/unsigned warnings in tests and code
* validate that init=0 is valid starting value and raise error if not
* fix diag_pre_multiply loop bound
Doc
---------------------------------
* made all user-suggested cleanups and changes to doc
* new basic programming section
* new chapter for new command line
v1.3.0 (12 April 2013)
======================================================================
Enhancements
----------------------------------
Modeling Language
* forward sampling (random draws from distributions)
in generated quantities
* added broadcast (repetition) functions for initializing
matrices, vectors, and arrays
* better error messages in parser
* additional distributions:
+ exp_mod_normal
+ gumbel
+ skew_normal
* additional functions:
+ mdivide_right_spd
+ mdivide_left_spd
+ owenst
+ columns_dot_product
+ rows_dot_product
* broadcast (repetition) functions for vectors, arrays, matrices
+ rep_arrray
+ rep_matrix
+ rep_row_vector
+ rep_vector
Command-Line
* added option to display autocorrelations in the command-line program
to print output
* changed default point estimation routine from the command line to
use Nesterov's accelerated gradient method, added option for point
estimation with Newton's method
RStan
* added method as.mcmc.list()
* compatibility with R 3.0.0
C++/Internal
* refactored math/agrad libs in C++ to separate files/includes,
remove redundant code, more unit tests for existing code
* added chainable_alloc class for caching solver results
* generalized VectorView with seq_view
* templated out generated code for efficient double-only operation
on model log probs w/o gradients
Doc
* additions to user's guide w. sample models
+ stochastic volatility example with source, optimized source,
simulation
+ time series, moving average, standardization for linear
regression, hidden Markov models, with examples
* manual's index is now hyperlinked
* added additional acknowledgements to manual
* added full description of differences between sampling
statement and lp__
* fixed general normal mixture model example
Testing
* split unit tests from distribution tests
Bug Fixes
----------------------------------
* fixed derivative in multi_normal_prec distribution function
* double-based log_prob functions return the same value as var-based
log_prob_grad functions
* calls to lgamma are now using boost's lgamma function
* patched transform to work with Eigen 3.2 beta
* all probability distribution functions and cumulative distribution
functions behave properly with 0 length vector arguments
* fixed error in definition of hypergeometric pmf
* fixed arguments to nesterov optimization ctor in command
* fixed issue with initialization matrices being read improperly
* Use fabs() instead of abs() in unit_vector_constrain.
* typos in the manual
* rstan:
+ fixed crash in R when index is out of bounds using set_cppo("fast")
+ io_context fix skipping len=0
+ fix the typo in manual (dims -> dim)
+ add require(inline) to fix the problem with loading sysdata.rda
v1.2.0 (6 March 2013)
======================================================================
Enhancements
----------------------------------
* full mass matrix estimation during warmup
* expose model log_prob and gradient functions in RStan for use
in other packages (such as optimizers)
* command-line program to display output from multiple chains
with parameter-by-parameter mean, se, sd, quantiles, and R-hat
* probability function speed improvements with vectorization
* created Stan contributed repositories for user-contributed
and experimental features (first entry is an emacs mode)
* modified makefiles so targets are the same under Windows,
Linux, and Mac
New Functions
----------------------------------
* most of the cumulative distribution functions (see the documentation
index for the full list of supported functions)
* added monitor() function in RStan
Bug Fixes
----------------------------------
* disabled Boost asserts in parser to quiet R's warnings
* enabled prints in generated quantities block
* various documentation patches
* fixed memory leak in matrix operations leading to leaks in
multivariate probability function use
* wrapped call to gradient log prob to catch unexpected exceptions
* fixed matrix resize issue on Windows that caused models to fail
at optimization levels above 0
* fixed bug in print preventing hyphens or grave accents from
priting
* fixed issue preventing matrix rows from being assigned on the
left side of an assignment statement
* clearer error messages on matrix and other function arguments
v1.1.1 (5 February 2013)
======================================================================
Bug Fixes
----------------------------------
* fixed bug in comparison operators, which swapped operator< with
operator<= and swapped operator> with operator>= semantics
* auto-initialize all variables to prevent segfaults
* atan2 gradient propagation fixed
* fixed off-by-one in NUTS treedepth bound so NUTS goes
at most to specified tree depth rather than specified depth + 1
* various compiler compatibility and minor consistency issues
* fixed bug in metaprogram preventing lower/upper bound constraints
on matrices
* fixed print error for number of kept samples
* fixed floating point literal precision issue in code generation
* fixed bug in bernoulli_log for boundary chance of success
theta=0 or theta=1
* many doc patches (mostly due to user comments -- thanks!)
* replace boost sign() to avoid compiler conflicts
* trapping mismatched dimension assignments in arrays,
matrices, and vectors
Enhancements
----------------------------------
* user's guide chapters w. sample models
+ gaussian processes
+ measurement error and meta-analysis
+ clustering (soft k-means, LDA, naive Bayes)
+ ARCH, GARCH model section in regression chapter
* sample models
+ hidden Markov models (HMMs)
+ non-negative matrix factorization (NNMF)
* speed improvements to multivariate models and matrix solvers
+ mdivide_left, mdivide_left_tri_low, mdivide_right,
mdivide_right_tri_low
+ determinant, log determinant
+ inverse
* much more extensive probability tests
* unstacked vari for multivariate auto-diff unfolding
* faster multiply self transpose / columns_dot_self
* cleaned up error messages for size mismatches in accessors
* simplified vector view expression template parameterization
* cleaned up many --pedantic compiler warnings
New Functions
----------------------------------
* log absolute determinant, with optimized gradients
* probability functions
+ multivariate normal, precision parameterization
* model timing and n_eff output in CSV for all test models
* ongoing vectorizations and reparameterizations
of probability functions
* faster Phi_approx computing an approximate cumulative unit
normal density
* added dims() function to extract dimensions of arrays of scalars,
vectors, and matrices
* added size() function to extract the number of elements in an array
v1.1.0 (17 Dec 2012)
======================================================================
-- Backward Compatibility Issue
* Categorical distribution recoded to match documentation; it
now has support {1,...,K} rather than {0,...,K-1}.
* (RStan) change default value of permuted flag from FALSE to TRUE for
Stan fit S4 extract() method
-- New Features
* Conditional (if-then-else) statements
* While statements
-- New Functions
* generalized multiply_lower_tri_self_transpose() to non-square
matrices
* special functions: log_inv_logit(), log1m_inv_logit()
* matrix special functions: cumulative_sum()
* probability functions: poisson_log_log() for log-rate
parameterized Poisson
* matrix functions: block(), diag_pre_multiply(), diag_post_multiply()
* comparison operators (<, >, <=, >=, ==, !=)
* boolean operators (!, ||, &&)
* allow +/- inf values in variable declaration constraints
-- RStan Improvements
* get_posterior_mean() method for Stan fit objects
* replaced RcppEigen dependency with include of Eigen source
* added read_stan_csv() to create Stan fit object from CSV files of
the form written to disk by the command-line version of Stan
* as.data.frame() S3 method for Stan fit objects
-- Bug Fixes
* fixed bug in NUTS diagonal resulting in too small step sizes
* fixed bug introduced in 1.0.3 that hid line and column number
bug reporting
* added checks that data dimensions match as well as sizes
* removed non-symmetric versions of eigenvalues() and eigenvectors()
* testing identifiers are not reserved words in C++/Stan
* trapping/reporting locations of errors in data and init reads
* improvements in dump data format reader for more R compatibility
and more generality
* fix bug in bernoulli logit distro tail density
-- Code Improvements
* templated out matrix libs to reduce code duplication
* vectorized auto-dif for tcrossprod() and crossprod()
* optimizations in Wishart
* vectorization with efficiency improvements in probability distributions
-- Libraries Updated
* Eigen version 3.1.1 replaced with version 3.1.2
* Boost version 1.51.0 replaced with version 1.52.0
-- Manual Improvements
* New chapter on univariate and multivariate variable transforms
* Many consistency improvements and typo corrections
* Information on running command line in parallel from shell
v 1.0.3 Release Notes (25 Oct 2012)
======================================================================
Stan Bug Fixes:
-- error output in stanc now directed to standard error
-- catching all exceptions thrown in stanc to prevent core dumps
-- parser now accepts variable names starting with "int" and "real"
in first assignment after declaration
-- now catching unknown truncation cdfs and vectorizations in stanc
-- (hopefully) less scary message for domain error rejects
-- removed use of assert(); replaced with exceptions where
appropriate
-- fixed boundary condition on reporting max init retry failures
-- fixed initialization errors in tests that failed on some platforms
-- improved error checking for matrix size args to prevent segfaults
-- fixed boundary condition on bounded transform to allow
beta(0.8,0.8) samples near 0 or 1
Stan New Features:
-- mdivide_left_tri_low, mdivide_right_tri_low functions
-- all univariate continuous densities vectorized
-- better error checking for transforms
-- new error return type in stanc for invalid arguments
-- lower and upper bounds for vectors, row vectors, and matrices
-- command parameter refresh <= 0 turns off iteration reporting
-- int divisions produce warnings in stanc
-- errors caused by invalid transformed parameters include var name
-- various efficiency improvements and error handling for boundary
conditions and special cases of probability functions
-- simplified matrix code with heavier use of templating
Stan Manual Additions:
-- example of defining new distribution with parameters
-- diff report vs. previous versions
-- updated for range constraints on vector, row vector, matrix
-- updated Eigen licensing information (now MPL, was LGPL)
-- fixed alpha ordering issue in function index due to bolding
RStan Bug Fixes:
-- bug of setting parameter epsilon_pm wrongly for NUTS
-- fixed seed reset so results match Stan
RStan New Features:
-- return empty stanfit object upon error such as incorrect data
input, wrong argument specification, etc. Previously, it will
stop. The empty stanfit includes the compiled model, so it can be
reused.
-- add function stan_demo() to run examples included in Stan.
-- add function sflist2stanfit() to merge a list of stanfit objects
into one, to facilitate user-level parallelism.
-- add S3 method as.matrix, as.array, is.array, dim,
dimnames for stanfit objects.
-- specify seed using string of digits in addition to numbers
-- turn off refresh if value <= 0
V 1.0.2 Release Notes (28 Sep 2012)
----------------------------------------------------------------------
Bug Fixes:
-- check ranges for LHS of assignment to prevent seg faults
-- added matrix size and shape tests to avoid seg faults
-- changed matrix to throw domain_error rather than illegal_argument
-- removed template variable names from distribution error msgs
-- indexing fixed for arrays of matrix/vector/row_vector
-- fixed sd() and variance() to return 0.0 for sequences of size 1
-- fixed void return type in auto_covariance
-- patch truncation to return -inf for variates out of range
-- upgraded BUGS ring model to use constraints plus tan2()
New Features:
-- print statements
-- multiply_lower_tri_self_transpose function
-- vectorized several probability functions (see the manual)
Manual Additions:
-- programming guide: IRT models
-- new appendix: style guide
-- new appendix: migrating from Stan
-- new index: function and distribution index
v1.0.1
----------------------------------------------------------------------
Patch release.
v1.0.0
----------------------------------------------------------------------
First release.
Sync between RStan and Stan Command-line
========================================
Top-Level Command
Cmd: stan/gm/command.hpp
RStan: rstan/rstan/inst/include/rstan/stan_fit.hpp
rstan/rstan/inst/include/rstan/stan_args.hpp
rstan/rstan/R/rstan.R
libstan.a
Cmd: any XXX.cpp file added to makefile
RStan: rstan/rstan/src/YYY__XXX.cpp
stanc translator
Cmd: stan/command/stanc.cpp
R: rstan/rstan/src/stanc.cpp
output analysis
Cmd: stan/mcmc/chains.hpp
R: rstan/rstan/src/chains.cpp
var_context impl
Cmd:
R: rstan/rstan/inst/include/rstan/io/rlist_ref_var_context.hpp
makefiles
Cmd: add .cpp files, makefile, make/make*
R: rstan/rstan/src/Makefile{,.win}
boost/eigen version
Cmd: lib/boost_x.xx.x/, lib/eigen_x.x.x, etc.
R: rstan/rstan/src/Makefile{,.win}
rstan/rstan/R/options.R
author list
Cmd: web/mc-stan.org/development-team.html
R: rstan/rstan/DESCRIPTION
rstan/rstan/man/rstan.Rd
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...