pints
pints copied to clipboard
pints-team
Probabilistic Inference on Noisy Time Series
Another really interesting direction for Pints to go in is to look at methods for sampling from intractable (i.e. unlike the Gaussian problem that are solved by use of Kalman...
Allow a variety of options in SMC (potentially population MCMC too): - Any sort of MCMC kernel (for example, adaptive MCMC, HMC) can be used, - A range of possible...
Main paper: https://arxiv.org/abs/0912.2380 Python package: https://arxiv.org/abs/1606.03757
As a good example of a very simple / classical optimiser that requires sensitivities https://en.wikipedia.org/wiki/Levenberg%E2%80%93Marquardt_algorithm
> I can describe the phenomenon, as it appears in my own work: I am working with an SEIR model for which I am trying to infer one parameter beta....
After discussion today, seems like we should start the first examples by showing you need an error/logpdf, then move on to show how PINTS lets you define one for time...
It is the most important method but is not shown by default! https://pints.readthedocs.io/en/stable/error_measures.html#pints.ErrorMeasure
Should contain an example of optimisation using the hyperparameter interface, with either external bayesian optimisation or a pints optimiser doing the tuning This will help us figure out what/if we...