pints
pints copied to clipboard
pints-team
Probabilistic Inference on Noisy Time Series
Also played with boundaries, but that just caused the method to run out of momentum & get stuck so abandoned the idea. Made a PR anyway because in the meantime...
See #1105 Another AdaGrad variant. This one seems OK, but very slow, so didn't finish.
See #1105 Performs very poorly on the logistic problem, so either has some bug I can't spot or isn't worth the effort for our type of problems. Leaving this here...
When we log to CSV the header says `Time m:s` but the value shown is a float representing seconds
It should be possible to add a check in `Transformation.convert_boundaries()` - are the boundaries rectangular? `isinstance(boundaries, pints.RectangularBoundaries)` - is the transformation elementwise? `self.elementwise()` If so, a new RectangularBoundaries can be...
Fixes several oddities in ABC controller test: - A file called "True" was being written on every run - Logged output was not compared to expected results - Logging tests...
Hey, I worked briefly on this project a few years back looking at some ABC methods but essentially ran out of time and the code never made it to a...
It should be quite easy to add a Transformation class that takes 2 or more transformations as constructor arguments, and then just applies them all. Useful if, for example, you...
The Gaussian log-likelihood description (https://pints.readthedocs.io/en/stable/log_likelihoods.html#pints.GaussianLogLikelihood) in the MultiOutputProblem case is incorrect. There should be i dependence in the final sum. The log-likelihood descriptions are also inconsistent between different log-likelihoods. For...
And explain why - [ ] cmaes - [ ] xnes - [ ] snes