Programming with random control paths, where the goal is to estimate the probability of ended up on a certain state, conditional upon some input.

More specifically, what *I* usually use probabilistic programming for is Bayesian inference, and I think this is common enough that it is generally assumed.
The program represents our random generative model, an conditioning upon the observed data gives us updated distributions over parameters, or prediction, or whatever.

By convention, when we say Bayesian *programming* rather than merely *inference*, there is an implied emphasis.
I am indicating hope that my technique might su succeed in
doing inference for very complicated models indeed, possibly ones without
tractable likelihoods of any kind, maybe
Turing-complete models.
Not just your garden-variety
hierarchical model.
*Hope* in this context means something like “we provide the programming
primitives to, in principle, express the awful crazy likelihood structure of your
complicated problem, and to do something that looks like it might estimate the correct conditional density, but you are on your own in demonstrating that it actually does so, and how close it got in the time you had.”

Mostly these tools are based on Markov Chain Monte Carlo sampling which turns out to be a startlingly general way to grind out estimates of the necessary conditional probabilities. Some frameworks enable other methods such as classic conjugate priors for trivial (sub-)models variational methods of all stripes, including reparameterisation flows, and many hybrids of all of the above.

See George Ho of PyMC3/PyMC4 for an in-depth introduction into what might be desirable to solve these problems in practice.

A probabilistic programming framework needs to provide six things:

- A language or API for users to specify a model
- A library of probability distributions and transformations to build the posterior density
- At least one inference algorithm, which either draws samples from the posterior (in the case of Markov Chain Monte Carlo, MCMC) or computes some approximation of it (in the case of variational inference, VI)
- At least one optimizer, which can compute the mode of the posterior density
- An autodifferentiation library to compute gradients required by the inference algorithm and optimizer
- A suite of diagnostics to monitor and analyze the quality of inference

See also Col Carroll’s overview of several trendy frameworks. This includes some I did not include here due to exhaustion and choice paralysis. Check the dates on all these; as a hip research area, there is a constant flux of new frameworks into and out of use.

## Funsors

I’ve seen *funsors* mentioned in this context.
I gether they are some kind of graphical model-inference abstraction.
Do they do anything useful?
Obermeyer et al. (2020):

It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework. Noting that the versatility of modern automatic differentiation frameworks is based in large part on the unifying concept of tensors, we describe a software abstraction for integration —

functional tensors— that captures many of the benefits of tensors, while also being able to describe continuous probability distributions. Moreover, functional tensors are a natural candidate for generalized variable elimination and parallel-scan filtering algorithms that enable parallel exact inference for a large family of tractable modeling motifs.…This property is extensively exploited by the Pyro probabilistic programming language (Bingham et al., 2018) and its implementation of tensor variable elimination for exact inference in discrete latent variable models , in which each random variable in a model is associated with a distinct tensor dimension and broadcasting is used to compile a probabilistic program into a discrete factor graph. Functional tensors (hereafter “funsors”) both formalize and extend this seemingly idiosyncratic but highly successful approach to probabilistic program compilation by generalizing tensors and broadcasting to allow free variables of non-integer types that appear in probabilistic models, such as real number, real-valued vector, or real-valued matrix. Building on this, we describe a simple language of lazy funsor expressions that can serve as a unified intermediate representation for a wide variety of probabilistic programs and inference algorithms. While in general there is no finite representation of functions of real variables, we provide a funsor interface for restricted classes of functions,including lazy algebraic expressions, non-normalized Gaussian functions, and Dirac delta distributions.

Sounds like this lands not to far from message passing ideas?

### MCMC considerations

Maybe see MCMC for now.

### Variation inference considerations

Maybe see variational inference for now.

## Toolkits

### Stan

Stan is the inference toolbox for broad classes of
Bayesian model and the *de facto* reference point.
If your problem CAN be handled by Stan, this is a highly recommended option.
Often seen in concert with brms which makes it easier to use for various standard regression models.

Stan breaks down in certain circumstances. It does not naturally express neural-network models well, and indeed we have reason to be concerned that the posterior simulations will be nasty with very high dimensional parameter vectors

Stan does support some variational inference, although last time I checked (2017) it was pure nonsense and not recommended.

See the Stan notebook.

### Pyro

pytorch + bayes = pyro. For rationale, see the pyro launch announcment:

We believe the critical ideas to solve AI will come from a joint effort among a worldwide community of people pursuing diverse approaches. By open sourcing Pyro, we hope to encourage the scientific world to collaborate on making AI tools more flexible, open, and easy-to-use. We expect the current (alpha!) version of Pyro will be of most interest to probabilistic modelers who want to leverage large data sets and deep networks, PyTorch users who want easy-to-use Bayesian computation, and data scientists ready to explore the ragged edge of new technology.

As a friendly, well-documented framework without the designed-during-interdepartmental-turf-war feel of the tensorflow frameworks, this is a good default option.

### Numpyro

Numpyro is an alternative version of pyro whcih uses [jax]./jax.html) for autodiff. In line with the general jax aesthetic it is elegant, fast, badly documented and missing some conveniences.

### Edward/Edward2

From Blei’s lab, leverages trendy deep learning machinery, tensorflow for variational Bayes and such.

This is now baked in to tensorflow as a probabilistic programming interface.

### TensorFlow Probability

Another Tensorflow entrant. Low-level and messy. Used in Edward2, above, but presumably more basic. The precise relationships between these tensorflow things is complicated enough that it is a whole other research project to pick it apart.

### pyprob

`pyprob`

: (Le, Baydin, and Wood 2017)

pyprob is a PyTorch-based library for probabilistic programming and inference compilation. The main focus of this library is on coupling existing simulation codebases with probabilistic inference with minimal intervention.

The main advantage of pyprob, compared against other probabilistic programming languages like Pyro, is a fully automatic amortized inference procedure based on importance sampling. pyprob only requires a generative model to be specified. Particularly, pyprob allows for efficient inference using inference compilation which trains a recurrent neural network as a proposal network.

In Pyro such an inference network requires the user to explicitly define the control flow of the network, which is due to Pyro running the inference network and generative model sequentially. However, in pyprob the generative model and inference network runs concurrently. Thus, the control flow of the model is directly used to train the inference network. This alleviates the need for manually defining its control flow.

The flagship application seems to be etalumis (Baydin et al. 2019) a probablistic programming framework with emphasis AFAICT on Bayesian inverse problems.

### Turing.jl

`Turing.jl`

is a Julia library for (universal) probabilistic programming. Current features include:

- Universal probabilistic programming with an intuitive modelling interface
- Hamiltonian Monte Carlo (HMC) sampling for differentiable posterior distributions
- Particle MCMC sampling for complex posterior distributions involving discrete variables and stochastic control flows
- Gibbs sampling that combines particle MCMC and HMC

It is one of many julia options, and includes MCMC toolkit `AdvancedHMC.jl`

### PyMC3

The PyMC family creates many probabilistic programming ideas and blogposts and also code, and has been doing so since the mid 2000s. They seem an excellent destination to learn about probabilistic programming, although not the best place to find stable, finished products, even by the mercurial standards of this field.

PyMC3 is python+Theano, although they have ported theano to jax and renamed it Aesara.
They claim this is fast and it might be an easy way to access jax-accelerated sampling if Numpyro feels to exhausting.^{1}

See Chris Fonnesbeck’s example in python.

Thomas Wiecki, Bayesian Deep Learning demonstrates some variants with PyMC3.

### Mamba.jl

Mambais an open platform for the implementation and application of MCMC methods to perform Bayesian analysis in julia. The package provides a framework for (1) specification of hierarchical models through stated relationships between data, parameters, and statistical distributions; (2) block-updating of parameters with samplers provided, defined by the user, or available from other packages; (3) execution of sampling schemes; and (4) posterior inference. It is intended to give users access to all levels of the design and implementation of MCMC simulators to particularly aid in the development of new methods.Several software options are available for MCMC sampling of Bayesian models. Individuals who are primarily interested in data analysis, unconcerned with the details of MCMC, and have models that can be fit in JAGS, Stan, or OpenBUGS are encouraged to use those programs.

Mambais intended for individuals who wish to have access to lower-level MCMC tools, are knowledgeable of MCMC methodologies, and have experience, or wish to gain experience, with their application. The package also provides stand-alone convergence diagnostics and posterior inference tools, which are essential for the analysis of MCMC output regardless of the software used to generate it.

### Gen

`Gen`

:

`Gen`

simplifies the use of probabilistic modeling and inference, by providing modeling languages in which users express models, and high-level programming constructs that automate aspects of inference.Like some probabilistic programming research languages, Gen includes universal modeling languages that can represent any model, including models with stochastic structure, discrete and continuous random variables, and simulators. However, Gen is distinguished by the flexibility that it affords to users for customizing their inference algorithm.

Gen’s flexible modeling and inference programming capabilities unify symbolic, neural, probabilistic, and simulation-based approaches to modeling and inference, including causal modeling, symbolic programming, deep learning, hierarchical Bayesiam modeling, graphics and physics engines, and planning and reinforcement learning.

It has an impressive talk demonstrating how you would interactively clean data using it.

### Greta

greta models are written right in R, so there’s no need to learn another language like BUGS or Stan

greta uses Google TensorFlow

I wonder *how* it uses Google Tensorflow.

### Soss.jl

Soss is a library for probabilistic programming.

Let’s jump right in with a simple linear model:

```
using Soss
m = @model X begin
β ~ Normal() |> iid(size(X,2))
y ~ For(eachrow(X)) do x
Normal(x’ * β, 1)
end
end;
```

In Soss, models are first-class and function-like, and “applying” a model to its arguments gives a joint distribution.

Just a few of the things we can do in Soss:

- Sample from the (forward) model
- Condition a joint distribution on a subset of parameters
- Have arbitrary Julia values (yes, even other models) as inputs or outputs of a model
- Build a new model for the predictive distribution, for assigning parameters to particular values

How does it do all these things exactly?

### Miscellaneous julia options

`DynamicHMC.jl`

does Hamiltonian/NUTS sampling in a raw likelihood setting.

Miletus is a financial product and term-structure modeling package that is available for quant stuff in Julia as part of the paid packages offerings in finance. Although it looks like it is also freely available?

### Inferpy

InferPy seems to be a higher-level competitor to Edward2?

### Zhusuan

ZhuSuan is a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan provides deep learning style primitives and algorithms for building probabilistic models and applying Bayesian inference. The supported inference algorithms include:

- Variational inference with programmable variational posteriors, various objectives and advanced gradient estimators (SGVB, REINFORCE, VIMCO, etc.).
- Importance sampling for learning and evaluating models, with programmable proposals.
- Hamiltonian Monte Carlo (HMC) with parallel chains, and optional automatic parameter tuning.

### Church/Anglican

Church is a general-purpose Turing-complete Monte Carlo lisp-derivative, which is unbearably slow but does some reputedly cute tricks with modeling human problem-solving, and other likelihood-free methods, according to creators Noah Goodman and Joshua Tenenbaum.

See also Anglican, which is the same but different, being built in clojure, and hence also leveraging browser Clojurescript.

### WebPPL

WebPPL is a successor to Church designed as a teaching language for probabilistic reasoning in the browser. If you like Javascript ML.

### BAT

See also BAT the Bayesian Analysis Toolkit, which does sophisticated Bayes modelling although AFAICT uses a fairly basic Metropolis-Hasting Sampler?

## References

*Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation*, 221–36. PLDI 2019. New York, NY, USA: ACM. https://doi.org/10.1145/3314221.3314642.

*Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation*, 571–85. PLDI 2018. New York, NY, USA: ACM. https://doi.org/10.1145/3192366.3192399.

*Proceedings of the 2Nd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages*, 52–57. MAPL 2018. New York, NY, USA: ACM. https://doi.org/10.1145/3211346.3211350.

*Journal of Educational and Behavioral Statistics*40 (5): 530–43. https://doi.org/10.3102/1076998615606113.

*Journal of Statistical Software*76 (1). https://doi.org/10.18637/jss.v076.i01.

*Proceedings of the ACM on Programming Languages*3 (January): 1–30. https://doi.org/10.1145/3290348.

*Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS)*, 54:1338–48. Proceedings of Machine Learning Research. Fort Lauderdale, FL, USA: PMLR. http://arxiv.org/abs/1610.09900.

*PeerJ Computer Science*2 (April): e55. https://doi.org/10.7717/peerj-cs.55.

*ICLR*. http://arxiv.org/abs/1701.03757.

PyMC4, despite what you might think due to the jetsam of an earlier hype cycle, is discontinued in favour of PyMC3. AFAICT PyMC4 was intended to be a tensorflow-backed system, so this is indicative of developing in tensorflow blighting every probabilistic programming system it touches.↩︎

## No comments yet!