File tree Expand file tree Collapse file tree 1 file changed +15
-6
lines changed Expand file tree Collapse file tree 1 file changed +15
-6
lines changed Original file line number Diff line number Diff line change 1
1
# Release Notes
2
2
3
-
4
3
## PyMC 3.3. (Unreleased)
5
-
6
- ### New features
7
-
8
- - Improve NUTS initialization ` advi+adapt_diag_grad ` and add ` jitter+adapt_diag_grad ` (#2643 )
4
+
5
+ ### New features
6
+
7
+ - Improve NUTS initialization ` advi+adapt_diag_grad ` and add ` jitter+adapt_diag_grad ` (#2643 )
8
+ - Added ` MatrixNormal ` class for representing vectors of multivariate normal variables
9
+ - Implemented ` HalfStudentT ` distribution
10
+ - New benchmark suite added (see http://pandas.pydata.org/speed/pymc3/ )
11
+ - Generalized random seed types
9
12
- Update loo, new improved algorithm (#2730 )
10
13
- New CSG (Constant Stochastic Gradient) approximate posterior sampling
11
14
algorithm (#2544 )
12
- ### Fixes
15
+
16
+ ### Fixes
17
+
18
+ - Fixed ` compareplot ` to use ` loo ` output.
19
+ - Improved ` posteriorplot ` to scale fonts
20
+ - ` sample_ppc_w ` now broadcasts
21
+ - ` df_summary ` function renamed to ` summary `
13
22
- Fixed ` compareplot ` to use ` loo ` output.
14
23
- Add test for ` model.logp_array ` and ` model.bijection ` (#2724 )
15
24
- Fixed ` sample_ppc ` and ` sample_ppc_w ` to iterate all chains(#2633 )
You can’t perform that action at this time.
0 commit comments