Reproduce “Nonparametric autoregressive estimation of probability distributions with parallel gradient boosting” 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
Rémy Chapelle
The authors build a joint density by estimating a marginal distribution, then conditional distributions in a chosen variable order. Their a-PGB method uses parallel-gradient-boosting conditional estimates and a univariate kernel density estimate for the first factor. It is best or second-best on 9 of 10 tested health datasets, though Alzheimer’s scoring required more computation than ARF.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.