probability

probability copied to clipboard

Adding the poisson quantile would be useful. As a use case, JAXNS uses quantiles to reparametrise. Below is a bisection approach accurate to rate of 1e4. ```python from functools import...

Joshuaalbert

How to calculate quantile and variance for the tensorflow_probability output?

3

I test the following code: [TFP Probabilistic Layers: Regression ](https://colab.research.google.com/github/tensorflow/probability/blob/master/tensorflow_probability/examples/jupyter_notebooks/Probabilistic_Layers_Regression.ipynb#scrollTo=5zCEYpzu7bDX) In "Custom PSD Kernel" section, I got yhat as the prediction for the test data. My purpose is to have...

mnozary

Dirichlet distribution sampling issue when jit_compile=True

1

It seems that some seeds produce nans when sampling from a Dirichlet distribution. Any idea why? Example script below that was tested on Google Colab. ``` import numpy as np...

LorenzoRimella

Feature Request: Implement trainable probability vectors for mixture distributions

1

Let's say we have a mixture model of the form P(x) = w1 P1(x) + w2 P2(x) + ... where the wi-s add up to 1. Right now, - We...

prasanthcakewalk

how to train neural network mixture model with tfp

2

Hello, I am trying to write a simple gaussian mixture model using tfp. Basically I want to implement an MDN with tensorflow probability, but i have a mistake `from keras.models...

isaaccs

Hi everyone, I have a time-series based ML pipeline. The algorithm used in it is Structural Time Series(STS) from Tensorflow here. We retrain it every day from start data to...

aktaseren

JAX backend doesn't use `jax.tree_util`

1

In this part, `expand_composites` is set to `False` and this prevents `jax.tree_util` for kicking in. https://github.com/tensorflow/probability/blob/64a70d0850f2ab6b69693b7fb728b7c6eb759a7e/tensorflow_probability/python/internal/backend/numpy/nest.py#L314-L320 The resulting problem is that we cannot use pytree incompatible with `dm_tree` Herę is...

krzysztofrusek

NotImplementedError: The adjoint sensitivity method does not support complex dtypes.

1

I am not able to differentiate code that involves a call to `tfp.math.ode.DormandPrince()` with complex arguments. I get a `NotImplementedError`. The error can be reproduced using the code below (based...

sriharikrishna

Fix typo: let's -> lets

2

fvoichick

Updated the Latex syntax in Variational_Inference_and_Joint_Distribut…

1

Updated the Latex syntax in Variational_Inference_and_Joint_Distributions.ipynb. In webpage, the Latex is not rendered as a formula. It is displaying as the Latex code. https://www.tensorflow.org/probability/examples/Variational_Inference_and_Joint_Distributions#overview_of_bayesian_variational_inference Thank you!

tilakrayal