#bayesian-inference

Sequential inference for state-space models in JAX: Kalman-family filters and smoothers, and SMC methods including particle filters, tempered SMC, and SMC².

Modeling Nonstationary Extreme Value Distributions

Antecedent is a typed causal-analysis compiler whose output is a qualified scientific claim. It keeps identification, structural uncertainty, empirical support, statistical uncertainty, assumptions, implementation evidence and provenance separate and machine-checkable all the way through execution and serialization.

Scientific computing platform on NumPy/SciPy/pandas/matplotlib: linear algebra, stats, optimization, signals, ML, information theory, chaos, Bayes, metaheuristics, geometry and RL.