tensorflow / tensorflow/probability

Bayesian Neural Network hierarchical prior

Open
#1,451 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.4k
Forks
1.1k
PR merge metrics
No merged PRs in 30d

Description

The default prior in Convolution3DReparametrization() is tfp.layers.default_multivariate_normal_fn which is an isotrophic Gaussian with mean 0 and standard devitaion1. The posterior is tfp_layers_util.default_mean_field_normal_fn() . Is it possible to specify a hierarchical model for prior and posterior for example, prior~N(0,sigma) and sigma~Gamma(a1,b1)? How can I implement this in Tensorflow probability, may be with tfd.JointDistributionSequential?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by examining the prior and posterior callables named in the issue: tfp.layers.default_multivariate_normal_fn and tfp_layers_util.default_mean_field_normal_fn. Investigate whether JointDistributionSequential can express the requested hierarchical prior and posterior, and define what supported implementation or documentation would count as done.

Written by the indexing model from the issue text.

Assessment

Tech stack
tensorflow
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.