search

joshspeagle / dynesty

Dynamic Nested Sampling package for computing Bayesian posteriors and evidences
https://dynesty.readthedocs.io/
MIT License
357 stars 77 forks source link

Runs randomly crashing with random number error #206

Closed Jammy2211 closed 3 years ago

Jammy2211 commented 4 years ago

Having an amazing time with Dynesty, but recently found runs crashing with the following error:

`
File "/home/jammy/PycharmProjects/PyAuto/PyAutoFit/autofit/non_linear/nest/dynesty.py", line 335, in _fit print_progress=not self.silence,

File "/home/jammy/PycharmProjects/VirtualEnvs/PyAuto/lib/python3.6/site-packages/dynesty/sampler.py", line 928, in run_nested add_live=add_live)):

File "/home/jammy/PycharmProjects/VirtualEnvs/PyAuto/lib/python3.6/site-packages/dynesty/sampler.py", line 782, in sample u, v, logl, nc = self._new_point(loglstar_new, logvol)

File "/home/jammy/PycharmProjects/VirtualEnvs/PyAuto/lib/python3.6/site-packages/dynesty/sampler.py", line 380, in _new_point u, v, logl, nc, blob = self._get_point_value(loglstar)

File "/home/jammy/PycharmProjects/VirtualEnvs/PyAuto/lib/python3.6/site-packages/dynesty/sampler.py", line 364, in _get_point_value self._fill_queue(loglstar)

File "/home/jammy/PycharmProjects/VirtualEnvs/PyAuto/lib/python3.6/site-packages/dynesty/sampler.py", line 333, in _fill_queue point, axes = self.propose_point()

File "/home/jammy/PycharmProjects/VirtualEnvs/PyAuto/lib/python3.6/site-packages/dynesty/nestedsamplers.py", line 624, in propose_live ell_idx = ell_idxs[self.rstate.randint(nidx)]

File "mtrand.pyx", line 743, in numpy.random.mtrand.RandomState.randint

File "_bounded_integers.pyx", line 1260, in numpy.random._bounded_integers._rand_int64 ValueError: low >= high ` We're using Dynesty v1.0.1.

As far as I can tell, we didn't used to get these errors and haven't changed much about Dynesty (I don't think we've even updated to a new version) and it seems to be specific to certain models. Any ideas? Could an update to NumPy have done this (we're using v1.18.2 but again I don't think this has been updated recently).

joshspeagle commented 4 years ago

Most likely this indicates a bounding error similar to #178. I would double-check the behavior of the bounding distributions right before crashing. It's possible updating to the dev branch on GitHub might solve these, but as more recent issues have found (#204, #205) there are still some improvements I need to make.

joshspeagle commented 3 years ago

A very late follow-up to this, but I believe the recent improvements to the stability and behaviour of the bounding distributions (#219 and others) should now resolve this and other similar issues, so I'm tentatively closing this.