Ricardo Vieira

Scan Gibbs example is outdated and wrong

1

This section of the Scan documentation has several issues: https://aesara.readthedocs.io/en/latest/library/scan.html#using-shared-variables-gibbs-sampling 1. Binomial no longer accepts `n`, `p` as keyword arguments 2. Outputs info is wrong because it uses a `float`...

Apply JAX JIT more selectively

9

It seems JAX JIT is fundamentally more limited in the types of graphs that it can handle compared to Aesara's C and Numba backends, as described in https://github.com/aesara-devs/aesara/issues/43, https://github.com/aesara-devs/aesara/issues/68, and...

https://github.com/aesara-devs/aesara/blob/7f8af9bc28755d93dca3afff2534a8a5f5ecbd80/aesara/tensor/shape.py#L531-L540

`local_dimshuffle_rv_lift` does not handle dimensions dropped by `DimShuffle`

4

```python import aesara import aesara.tensor as at from aesara.graph import FunctionGraph from aesara.tensor.random.opt import local_dimshuffle_rv_lift x = at.random.normal(0, 1, size=(1, 2)).dimshuffle(1) fg = FunctionGraph(outputs=[x]) print(local_dimshuffle_rv_lift.transform(fg, x.owner)) # False x =...

Add gufunc signature to SymbolicRandomVariables

3

## Description This meta-info is necessary to reason about batch dims of SymbolicRandomVariables in the context of https://github.com/pymc-devs/pymc-experimental/pull/300 This is probably what we should use for RandomVariables, instead of defining...

Run convergence checks when using JAX samplers

1

## Description Also: * Refactored code to avoid so much duplication * Inlined some very short one-use functions * Got rid of the many verbose log time statements * Always...

`sample_posterior_predictive` does not consider changes in "ConstantData" and "Constant coords"

1

### Description The existing checks assume the same model is used between sample and sample_posterior_predictive, in which case the only variable that can be changed are mutable ones. However if...

### Description Currently, there is no information about dimensionality of variables: ```python import pymc as pm from pymc.printing import str_for_model with pm.Model(coords={"trial": range(10)}) as m: x = pm.Normal("x") y =...

Allow Truncation of CustomDist

1

This is now possible: ```python import pymc as pm import numpy as np def maxwell_dist(scale, size): return pm.math.sqrt(pm.ChiSquared.dist(nu=3, size=size)) * scale scale = 5.0 x = pm.CustomDist.dist(scale, dist=maxwell_dist) trunc_x =...

Use same API for defining internal and external Nuts kwargs

2

### Description User on discourse [reported](https://discourse.pymc.io/t/how-can-i-set-the-maximum-tree-depth-for-the-nuts-method-from-the-numpyro-library/12258): > > How can I set the maximum tree depth for the NUTS method from the numpyro library? > The way described in the...