Posts by Juan Orduz

Boundary Conditions in the Hilbert Space GP Approximation

A Gaussian process (GP) prior describes a distribution over functions before we observe data. Its covariance function controls how function values vary together. For a stationary GP, this relationship depends on the separation between inputs, not their absolute positions.

Read more ...


Hidden Markov Models in PyMC: marginalize and recover a DiscreteMarkovChain

A hidden Markov model (HMM) describes a system that moves through a sequence of hidden discrete states, where each state emits a noisy observation. We never see the states directly; we only see the emissions, and we want to reason backward to the states that most likely produced them.

Read more ...


Modeling Heteroscedasticity with BART

In this notebook we show how to use BART to model heteroscedasticity as described in Section 4.1 of pymc-bart’s paper [Quiroga et al., 2022]. We use the marketing data set provided by the R package datarium [Kassambara, 2019]. The idea is to model a marketing channel contribution to sales as a function of budget.

Read more ...