foerster

Probabilistic inference in forkable worlds, for Clojure. Tutorials rendered from source; API reference on cljdoc.

Tutorials

• Getting Started — a first model, sample and observe, SMC, the posterior
• Choosing an Inference Algorithm — importance sampling, SMC, particle MCMC, MCMC, BBVI on known posteriors; guides; composed kernels
• Models in Worlds — canonical forks, budgets, what cannot be copied
• Blocks and HMC — numerical blocks, HMC-within-Gibbs, checking gradients
• Streaming SMC — online filtering against the Kalman filter
• Programmable Inference — the generative function interface, MH by selection, involutive MCMC
• Steering a Process — tilting a process by a reward with SMC; trajectories as training data
• Interventions and Counterfactuals — seeing, doing, and what would have been
• A Gallery of Classic Models — pencils, regression, seven scientists, label switching, branching, coal-mining disasters and eight schools, each against an exact answer

Guides

• Language — sites, addresses, and the rules of the spin macro
• Algorithms — every inference entry point and its options
• Posteriors — reading a measure: summaries, diagnostics, evidence
• Extending — policies, proposals, MH moves and kernels
• Worlds — canonical worlds, their lifecycle, failure and recovery
• Distributions and Reproducibility — foerster.dist, seeds and streams
• Design — inference as handlers of spindel savepoints
• Literature — the papers and systems foerster builds on