diag | Network diagnostic tool | Networking library

Since object like "QuadTypeIndependenceTest" and "ScalarIndependenceTest" are created from the results of coin packages, there is specific function to extract the pvalue, using coin::pvalue(obj), Special thanks for pointing @AntoniosK

This is a two-part question:

• what priors should I use for a multivariate random effect where the likelihood is concentrated at small values? (I am assuming that this is the reason you are looking for an alternative to the default inverse Wishart priors) [more suitable for CrossValidated]
• which of these are available in MCMCglmm, and how do I implement them there? [good for Stack Overflow]

The general trick is to decompose the covariance matrix into a multivariate component (the correlation matrix or inverse correlation matrix or something) and a vector of scaling parameters for the standard deviations (or inverse standard deviations); Lemoine suggests U(0,100) for the scaling priors, which I think is bad (why flat? I can't get to the precise page of Gelman and Hill 2007 where they discuss which distribution to use for scaling priors ... but I would be a little surprised if they actually recommended a uniform distribution on the variance scale ...)

update having actually looked at your code (!): I think you're doing the right thing, except that nu=0.002 seems really extreme; see end for that discussion.

This is basically what MCMCglmm does, but it uses a different (IMO better) choice for the scaling priors. It sounds scary:

These priors are all from the non-central scaled F-distribution, which implies the prior for the standard deviation is a non-central folded scaled t-distribution (Gelman, 2006).

but it boils down to choosing four parameters, only two of which you really have to think about.

• V: the prior mean variance (or the prior mean covariance matrix, if you have a multivariate random effect term). According to the course notes, "without loss of generality V can be set to one" (or in the case of a multivariate model, to an identity matrix)
• alpha.mu: we almost always want this to be zero (or as in your example, a vector of zeros); that way the prior for the standard deviation will be a Student t distribution. (There may be a use case for alpha.mu != 0, but I've never run across it.)
• alpha.V: with V set to 1 (or an identity matrix), this is the prior mean of the covariance matrix. A diagonal matrix with a reasonable scale for your problem is a good choice
• nu: the shape parameter; as nu → ∞ we get a half-Normal prior for the standard deviations, with nu=1 we get a Cauchy distribution. Smaller values have fatter tails (less conservative/allowing broader samples, but also giving more danger of weird sampling behaviour in the tails).

For the univariate case Hadfield says the t prior with V=1 is

According to Microsoft, it was caused by Windows Defender:

We have identified an underlying issue in Windows Defender which we believe to be the root cause for most folks. The fix has already been deployed to Windows Update, the steps to get / verify are below:

1. From PowerShell run Get-MpComputerStatus Verify AntivirusSignatureVersion is >= 1.341.82.0 a.
2. If the signature version is < 1.341.82.0 run Windows Update to get the latest version and then reverify
3. Reboot

After this profiling should work in ETW based profilers.

If all elements are either 0 or 1 (as I believe your picture shows), then:

Try:

I think I got the problem. First of all below is the way by which we can reproduce the error & the way you have proceed :

We can initialize a dataset and then rbind instead of printing

According to the custom_vjp docs:

The output of bwd must be a tuple of length equal to the number of arguments of the primal function

So the return statement in the backward pass should look like this:

So it looks I've answered my own question. Its not exactly what i was expecting but it does work. What I noticed was that modifying any of the lists board[0], board[1] and board[2] (which happen to be the rows) modified the elements in board and vice versa.

So I figured if I convert board to a numpy array and use its indexing to get the columns, it would allow me to do this with columns as well. So that would make 6 of the possible winning options. luckily, the array.diagonal() allowed me to achieve the same with the diagonal elements too.