probability

probability copied to clipboard

Hi, Bayesian Vector Autoregression is quite popular in macroeconomics, if your team could set up an example for this, that would be good for economic researchers from MATLAB to Python....

richardmkit

Implement quantile for `Mixture` and `MixtureSameFamily`.

14

when will the inverse cdf of these kinda distribution quantile be implemented? I have nightly version installed but found quantile not implemented.

moonman925

DenseFlipOut layer

2

I am using the **DenseFlipOut** layer, I see that it has a mean_normal distribution over the weights and the biases by default, but I was wondering how these distributions are...

pks42

Hi, I have been tinkering with the `SoftmaxCentered` bijector but I would like help understanding how the determinant of the Jacobian is calculated. I've already found the function [SoftmaxCentered._inverse_log_det_jacobian](https://github.com/tensorflow/probability/blob/v0.23.0/tensorflow_probability/python/bijectors/softmax_centered.py#L122), which...

hylkedonker

Distributions are not independent for Empirical

1

While the [documentation states](https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Empirical#args) that > The first k dimensions index into a batch of independent distributions this is not the case for the implementation. As can be seen from...

sfo

Cannot compute gradient of Weibull parameters on second iteration

1

I am trying to learn the parameters of a Weibull distribution, but after the first iteration the gradients turn None: ```python import tensorflow as tf from tensorflow_probability import distributions as...

Kornel

Always-on dropout layer

2

**Feature** Add the ability to create "always-on" dropout layers as proposed [here](https://arxiv.org/abs/1703.04977). **Current behavior/state.** `tf.keras.layers.Dropout` operates differently at train and test time. It randomly drops node during training while simply...

janosh

Hi, I noticed the `quantile()` function of `tfd.Empirical` raises the following error: `AttributeError: 'function' object has no attribute 'percentile'`. ```python import tensorflow_probability as tfp tfd = tfp.distributions tfd.Empirical(samples=[1,2,3]).quantile(value=[0.1, 0.5]) >>>......

yusukemh

Memory leak for TFP distribution

1

Hi, I'm facing a memory leak issue with TFP distributions. Specifically, I have a custom function that samples from a Categorical distribution and returns the output: ``` def compute_categorical_distribution(classes_pred,dtype=np.int8,validate_args=True): #...

fotisdr

tf.vectorized_map not compatible with LinearGaussianStateSpaceModel forward_filter?

3

Hi all, I have a batch of data and want to conduct the Kalman filter for each observation set. My data is `observations =(batch, num_time_lens, feature_dim)` so I use `tf.vectorized_map`...

Qiustander