Tim Reichelt
Tim Reichelt
Stan has a nice automated way to check whether any of the HMC diagnostics hint at problems in the inference. In CmdStan this can be done using [diagnose](https://mc-stan.org/docs/2_25/cmdstan-guide/diagnose.html). The source...
When sampling from a model with NUTS then the `Chains` object that is returned contains a lot of internal fields which seem to be undocumented. Are those fields documented somewhere?...
The link in the second sentence of the parallel sampling sentence points to a webpage which does not seem to exist (https://turing.ml/dev/docs/library/advancedhmc/parallel_sampling). Is this a page that is supposed to...
The link in the README pointing towards more information about the vectorized implementation about static HMC points to a webpage which errors with 404: ``` It also supports vectorized sampling...
I was wondering whether there is a vectorised implementation of MH (i.e. running several chains in parallel) available in this repo? I've seen that there is a vectorised implementation in...
This is an initial bare bones implementation of the [Divide, Conquer, Combine](https://arxiv.org/abs/1910.13324) inference algorithm for programs with stochastic support as discussed in #1697. I have also included a simple example...
I was wondering whether there would an interest to add inference methods which support programs with stochastic support? If yes, I would be willing to add inference methods from the...
### Issue Description Currently the `cdf` function for `InverseGamma` returns obviously wrong values. The current implementation returns a *monotonically decreasing* function which clearly cannot be right. On closer inspection, currently...
There's currently no implementation of group normalization in the [NNX normalization layers](https://flax.readthedocs.io/en/latest/api_reference/flax.nnx/nn/normalization.html). Is there a specific reason for why it is not implemented at the moment? If not I would...
Thank you for developing this useful package! I installed `ldcpy` to calculate the data-SSIM (`ssim_value_fp_fast`). However, on my own dataset, I could not initialise a `Diffcalcs` instance because it does...