Bryor Snefjella

predict.brmsfit with imputed missing values

7

Currently, predict.brmsfit returns an error when predictions are requested for all responses, and the new data contains NAs in variables that were imputed during fitting. A partial solution to this,...

Feature Request: Gumbel Mixture Models

2

It is possible to construct reparameterizable mixture distributions by replacing the categorical distribution with a gumbel (relaxed categorical) distribution. The ability to use a relaxed one-hot categorical distribution in mixture...

Feature Request: Alternative Horseshoe Parameterization as tfp distribution

3

The currently implemented version of the horseshoe distribution is not the parameterization that most ML papers use. This limits the ease of use of this as, for example, a prior...

Easy repetition of distribution parameters

2

Hi all, I'm trying to figure out if there is an implemented, general way of taking a tfp.distribution, repeating certain batch members, and making a new distribution to sample from....

Error when predicting with large N

1

I'm getting an error when trying to predict using gamboost, but the error only appears for me when the N becomes large. E.g. running this code with 10000 rows of...