Tom Minka

I'm confused about the use case of this. If the assemblies cannot be loaded normally, then how will inference work?

We could easily provide a function that generates the source code and doesn't try to compile it using the C# compiler. When you compile that code, you can use any...

It means that the eigenvalue algorithm being used is not converging for the given matrix. If you can get the debugger to stop on this line, you can inspect the...

If you are using the same InferenceEngine throughout, then this is expected since it thinks you are adding new variables to one giant model. If you want to create separate...

If you have many models with the same structure, then you should use ObservedValues to merge them into one model, as explained in the [TruncatedGaussian example](https://dotnet.github.io/infer/userguide/Truncated%20Gaussian%20tutorial.html). This will be significantly...

If you are using `Variable.ConstrainEqualRandom(x, dist)` to attach soft evidence, you can make `dist` a Variable whose ObservedValue changes. Setting `dist.ObservedValue` to uniform will remove the soft evidence. For examples...

> Curious why PR still in the "waiting" status I'm guessing it is a permissions issue. I created my own PR #495 from this branch and the builds are working.