probcomp / Gen.jl

What it does

• Multi-paradigm Bayesian inference via Sequential Monte Carlo, variational inference, MCMC, and more.
• Gradient-based training of generative models via parameter optimization, wake-sleep learning, etc.
• An expressive and intuitive modeling language for writing and composing probabilistic programs.
• Inference algorithms are _programmable_. Write custom proposals, variational families, MCMC kernels or SMC updates without worrying about the math.
• Support for Bayesian structure learning via involutive MCMC and SMCP³.