Tom Minka

Thanks for converting this example. I will add this code to the TestFSharp folder, if you don't mind. I am not able to reproduce the error that you are seeing....

I am using .NET framework version 4.0.30319.42000 mscorlib 4.7.3324.0 from Visual Studio 2017 15.9.8. It also works under .NET Core version 4.0.30319.42000 mscorlib 4.6.27317.03 @BuiltBy: dlab14-DDVSOWINAGE101 @Branch: release/2.1 @SrcCode: https://github.com/dotnet/coreclr/tree/67716e18103217d501c5901e5a7e9c4da7d044c8

You can find the code that I used at [DifficultyAbility.fs](https://github.com/dotnet/infer/blob/master/test/TestFSharp/DifficultyAbility.fs).

See the [README for the C# extension](https://github.com/OmniSharp/omnisharp-vscode/blob/master/debugger.md). Here is a summary: Launch Visual Studio Code. Select the Extensions button on the left, then install C# and the NuGet Package Manager...

What do you want those binaries to contain?

I am not able to reproduce this. When I try, it says "This example only runs with Variational Message Passing". Try editing RunMe.cs so that it doesn't run the ExampleBrowser...

If you change the algorithm in the browser, it will work correctly. It sounds like your issue is: "The code that I expected would change the algorithm does not work."

The T variable generated by this model can be negative. Therefore you must have some kind of link function to turn it into a Poisson rate. See section 3.2.2 of...

If you expand the MatrixMultiply as explicit pairwise sums and products and use VariationalMessagePassing, then it will allow you to use Gamma-distributed Z and W.

Message (7) is implemented in [infer/src/Runtime/Factors/Product.cs#AAverageLogarithm](https://github.com/dotnet/infer/blob/main/src/Runtime/Factors/Product.cs#L2117). Messages (2) and (7) come from [Variational Message Passing](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/bishop-vibes-jmlr-04.pdf) section 4.2. A concise form of those messages can be found in Table 1 of...