Comments (3)
Hi Jackson! This is a great request. Others might have more to say here, but I think the current state of things is that walking the TF graph is strongly discouraged, and code that tries to do so using unpublished APIs is subject to breakage without notice. The brittleness of graph-walking in Edward was a primary motivation for the development of Edward2, which uses its own tracing mechanism to avoid directly walking the TF graph.
Subject to this restriction, you might find that the expectation
utility (https://github.com/tensorflow/probability/blob/master/tensorflow_probability/python/monte_carlo.py#L29) does some of what you're asking for: given an explicit source of randomness, it returns a Monte Carlo expectation with unbiased stochastic gradient, using the reparametrization or score-function estimators as appropriate. You can use this to effectively construct stochastic computation graphs, albeit in perhaps a slightly lower-level way than you're thinking of. We'd certainly be excited about designs to make this sort of functionality more cleanly accessible.
from probability.
Is there a white paper somewhere outlining to scope of the API edward2 is planning to compass? Or is the main idea just to rewrite Edward in a less brittle way?
from probability.
@dustinvtran want to take this?
from probability.
Related Issues (20)
- Distribution Output Cannot Be Passed to Keras Layers HOT 1
- Distribution Output is Incompatible with Keras Dense Layers HOT 7
- Can you give an example of Bayesian Vector Autoregression based on TFP
- Normal Inverse Gaussian Outputs Positive log_prob HOT 4
- JAX backend doesn't use `jax.tree_util` HOT 1
- Sample from a partially known TensorShape inside the train_step function of a keras subclassed model HOT 1
- How to add new data to the pretrained Structural Time Series model in Tensorflow
- TurncatedNormal gives wrong results sometimes HOT 4
- Dirichlet distribution sampling issue when jit_compile=True HOT 1
- AttributeError: 'SymbolicTensor' object has no attribute 'log_prob' when exporting train signature with `IndependentNormal` layer HOT 1
- Add Poisson quantile
- Computing log_prob for tfd.Sample() with a different number of samples
- TruncatedCauchy gives wrong results sometimes
- `_parameter_properties` is not implemented for `LinearGaussianStateSpaceModel`
- tensorflow 2.16.1 breaks tensorflow-probability with Keras `3.0` API HOT 3
- `LinearGaussianStateSpaceModel` filtering initial state is incorrect
- Piecewise distribution
- Keras not accepting character `/` from build_factored_surrogate_posterior HOT 4
- A bug in Linear_Mixed_Effects_Models.ipynb
- Conditional input with multiple flows HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from probability.