support Lgamma and BroadcastTo Ops in order to support probabilistic models (Poisson distribution)

[lukasheinrich]

When trying to covnert a model that uses tensorflow_probability.distributions.Poisson I get the error

ValueError: Unsupported Ops in the model before optimization
Lgamma, BroadcastTo

In order to support probabilistic models using those libraries itwould be great if those Ops could be added

@kratsg @matthewfeickert

https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/lgamma
https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/broadcast-to

[dsmilkov]

Hi Lukas,

Can you share a bit about your model/use-case? There's a long tail of ops that TF.js is missing and we are trying to prioritize based on use-case.

[lukasheinrich]

hi @dsmilkov,

our specific use case is the computation of probabilistic models for high energy physics models at CERN, using this package:

https://github.com/diana-hep/pyhf

but I think being able to compute a Poisson distribution is probably of much broader appeal for any model using tensorflow probability.

[DirkToewe]

The rather monstrous PR#1356 contained a broadcastTo implementation. If You want, I can take it out and submit it as PR to the monorepo.

[lukasheinrich]

hi @DirkToewe I think that would be awesome and maybe easier to merge. Do you know anytone working on lgamma?

[DirkToewe]

No idea sorry. A float32/complex64 implementation of lgamma(z) for Re(z) > 0 can be found in:

"Numerical Recipes in C",
2nd edition,
chapter 6, page 213f.

It's C code but fairly easy to read and understand. Should be feasible to implement using existing TFJS functions as well.

[kratsg]

@DirkToewe -- copying here for usefulness

#include <math.h>

// Returns the value ln[Γ(xx)] for xx > 0.
float gammln(float xx)
{
//Internal arithmetic will be done in double precision, a nicety that you can omit if five-figure
// accuracy is good enough.
    double x,y,tmp,ser;
    static double cof[6]={76.18009172947146,-86.50532032941677,
                          24.01409824083091,-1.231739572450155,
                          0.1208650973866179e-2,-0.5395239384953e-5};
    int j;
    y=x=xx;
    tmp=x+5.5;
    tmp -= (x+0.5)*log(tmp);
    ser=1.000000000190015;
    for (j=0;j<=5;j++) ser += cof[j]/++y;
    return -tmp+log(2.5066282746310005*ser/x);
}

[annxingyuan]

Noting that BroadcastTo is also needed for the music transformer model.

[gaikwadrahul8]

Hi, @lukasheinrich

Apologize for the delayed response and I see this PR #2238 got merged for tf.broadcastTo but at the moment It seems like we haven't implemented Lgamma Op so just to confirm still are you looking to add this Lgamma Op please ?

If someone wants to contribute for Lgamma Op then you're always welcome please feel free to do that, please refer this link. Thank you!