Reproduce “Time Series Change Point Detection with Gaussian Processes” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Olga Isupova, Danil Kuzin, Fredrik Gustafsson, Lyudmila Mihaylova
The authors propose online change-point detection by testing whether a recent window fits a Gaussian-process model of the current regime. Changes are defined as shifts in the model’s hyperparameters, without specifying the next regime in advance. On bee-dance Sequence 1, adaptive GP-OLCDT has delay 2.79 steps versus 12 for GP-BOCPD; this is one sequence, not a general guarantee.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.