Posts
bayes3 changepoint1 data-analysis2 einsums2 ewma1 filtering4 kalman-filter2 linear-algebra1 non-stationary2 slides1 time-series1 uncertainty12025
Filtering notes (II): state-space modelsIntroduction to linear state-space models: basic properties, measures of uncertainty, and the ARMA model.
Filtering notes (I): signal plus noise modelsEssentials of signal-plus-noise models: best linear unbiased predictors, innovations, filtering, prediction, smoothing, and fixed-lag smoothing.
2024
[slides] Bayesian online learning in non-stationary environmentsA unifying framework and literature review for methods that perform Bayesian online learning in non-stationary environments.
Non-stationary coin tosses - an introduction to the Bayesian online changepoint detection model (BOCD)A detailed and simplified introduction to the Bayesian online changepoint detection (BOCD) model for binary data using a Beta-Bernoulli model.
A robust exponentially-weighted moving averageAn exponentially-weighted moving average (EWMA) is a special case of the Kalman filter (KF). The weighted-observation likelihood filter (WoLF) is an outlier-robust variant of the KF. Here, we create a 1D version of WoLF that resembles the EWMA and is robust to outliers.
2023
Deriving the Kalman filter in four stepsDerivation of the Kalman filter algorithm under a linear state-space model with Gaussian priors.
2021
Einsums in the wildIntroduction to the Einstein summation (einsums) and their use in machine learning.
GSoC 2021: end-of-summer reportFinal report for the Google Summer of Code (GSoC) 2021 program on converting Matlab examples to Jax for the book Probabilistic Machine Learning.
2020
A journey through pattern recognition and machine learningPersonal logs while reading the book Pattern Recognition and Machine Learning (PRML) by Christopher Bishop.