linsdex

A JAX-based library for linear stochastic differential equations, state-space models, and Gaussian inference. Use when working with time series interpolation, diffusion models, Kalman filtering, or probabilistic modeling with linear-Gaussian systems.

Work with probability path distributions for diffusion models, including bridge path marginals, memoryless sampling, and efficient batch computation. Use when you need to sample from or evaluate the distribution p(x_t | y_1) at intermediate times.

Perform inference in chain-structured Gaussian Conditional Random Fields using efficient message passing. Use for discrete-time probabilistic modeling, computing marginals, sampling joint distributions, or Kalman-style filtering and smoothing.

Convert between diffusion model representations including clean data predictions (y1), scores, probability flows, and drifts. Use when building or training diffusion-based generative models.

Work with Gaussian distributions in three parameterizations for numerical stability and efficiency. Use when you need to sample, combine distributions, or convert between mean/covariance and precision/natural forms.

Use specialized matrix types with symbolic tags for efficient linear algebra. Use when working with diagonal, block, or tagged matrices to avoid unnecessary dense computations.

Condition Linear SDEs on observations to interpolate sparse data, perform Bayesian inference on time series, or create bridges between boundary conditions. Use when working with time series interpolation, state estimation, or posterior sampling.