Releases: TuringLang/Turing.jl
Releases · TuringLang/Turing.jl
v0.32.2
v0.32.1
Turing v0.32.1
Merged pull requests:
- Re-export certain functionality from DynamicPPL (#2217) (@torfjelde)
- Export adtype
AutoTapir
(#2236) (@yebai)
Closed issues:
v0.32.0
Turing v0.32.0
Merged pull requests:
- Fixes to AD backend usage in
externalsampler
(#2223) (@torfjelde) - Bump DPPL version to 0.27 (#2225) (@torfjelde)
v0.31.5
Turing v0.31.5
Merged pull requests:
- Fix for
optimize
and:=
(#2224) (@torfjelde)
Closed issues:
- Issues with constrained parameters depending on each other (#2195)
v0.31.4
Turing v0.31.4
Features
- It is now possible to use
:=
to track deterministic quantities in the model.
Merged pull requests:
- Use
values_as_in_model
to extract the parameters from aTransition
(#2202) (@torfjelde)
Closed issues:
- Problems with deterministic distribution (#1335)
- Zygote's compilation scales badly with the number of
~
statements (#1754) - New Gibbs sampler based on
SimpleVarInfo
. (#1904) - LKJCholesky returns a Union (#2102)
ADVI
is not up-to-date on the AD side (#2186)- Model fails with an autograd error (#2189)
- Why are we passing
chunksize=0
toAutoForwardDiff
rather than using default? (#2203)
v0.31.3
Turing v0.31.3
Merged pull requests:
- Bump ADTypes compat entry to include version 1 (#2209) (@torfjelde)
v0.31.2
Turing v0.31.2
Merged pull requests:
- CompatHelper: bump compat for ADTypes to 1, (keep existing compat) (#2200) (@github-actions[bot])
- Improvements to
externalsampler
(#2204) (@torfjelde) - Revert "CompatHelper: bump compat for ADTypes to 1, (keep existing compat)" (#2207) (@torfjelde)
- Bump AdvancedPS version to 0.6.0 (#2210) (@THargreaves)
v0.31.1
Turing v0.31.1
Merged pull requests:
- Fix for #2205 (#2206) (@torfjelde)
Closed issues:
- ADVI errors for conditioned problems (#2205)
v0.31.0
v0.30.9
Turing v0.30.9
New features
Turing.Experimental
module where more experimental features will go, with the aim of eventually making its way intoTuring
proper.Turing.Experimental.Gibbs
is a new implementation of theGibbs
sampler which provides much greater flexibility specifying which variables should use which sampler. Note that this is in theTuring.Experimental
module, and thus will be prone to changes.
Merged pull requests:
- New Gibbs sampler using
condition
(#2099) (@torfjelde)