dynamax
dynamax copied to clipboard
Fix failing LinRegHMM test
Summary
This PR changes the parameters of the LinearRegressionHMM test to prevent it failing.
Details
At present the LinearRegressionHMM test_sample_and_fit test is failing. The monotonically_increasing assertion is failing as the log likelihoods quickly become jnp.nan.
I think this is fundamentally a question of the stability of the linear solve. I have made some changes to the inputs which are hopefully more robust to solving.
Changes:
- Replace
jnp.onesinput withjr.normal. - Reduce size of hidden state to 3.
There are likely more principled ways of choosing a more robust test case but in the interest of getting the test to pass I think it is helpful to make a simple change quickly.
Additional changes:
- Remove unused
datetimeimport and commented lines.