higrad: Statistical Inference for Online Learning and Stochastic Approximation via HiGrad (original) (raw)

Implements the Hierarchical Incremental GRAdient Descent (HiGrad) algorithm, a first-order algorithm for finding the minimizer of a function in online learning just like stochastic gradient descent (SGD). In addition, this method attaches a confidence interval to assess the uncertainty of its predictions. See Su and Zhu (2018) <doi:10.48550/arXiv.1802.04876> for details.

Documentation:

Downloads:

Linking:

Please use the canonical formhttps://CRAN.R-project.org/package=higradto link to this page.