Commit e8212f36 authored by Philipp Arras's avatar Philipp Arras
Browse files

Remove part about metric

parent d7a4ae80
......@@ -112,23 +112,11 @@ in a fashion which is compatible with our inference machinery called NIFTy.
\section*{Mathematical description of what NIFTy needs}
The Bayesian inference will be a minimization problem in the end. NIFTy comes
with a variety of minimizers in order to solve this problem. These minimizers
differ in their order. If you want to use only first order minimizers, you need
to provide the following two functions:
The abstract definition of what you'll need to implement is very short:
\item The log-likelihood $\mathcal H (d|s) := - \log \mathcal P (d|s)$ as a function of $s$.
\item Its derivative $\mathcal H' = \frac{\partial}{\partial s} \mathcal H (d|s)$.
If you want to use second order minimizers (which is definitely worth it),
another object is needed:
\item $\langle \mathcal H' \mathcal H'^\dagger \rangle_{\mathcal P (d|s)}$.
Note that for Gaussian, Poissonian and Bernoulli likelihoods this term doesn't
need to be calculated and implemented because NIFTy computes it automatically.
That's it. The rest of this paper explains what these formulae mean and how to
compute them. From now one, our discussion will become increasingly specific.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment