stochQN: Stochastic Limited Memory Quasi-Newton Optimizers

Implementations of stochastic, limited-memory quasi-Newton optimizers, similar in spirit to the LBFGS (Limited-memory Broyden-Fletcher-Goldfarb-Shanno) algorithm, for smooth stochastic optimization. Implements the following methods: oLBFGS (online LBFGS) (Schraudolph, N.N., Yu, J. and Guenter, S., 2007 <>), SQN (stochastic quasi-Newton) (Byrd, R.H., Hansen, S.L., Nocedal, J. and Singer, Y., 2016 <doi:10.48550/arXiv.1401.7020>), adaQN (adaptive quasi-Newton) (Keskar, N.S., Berahas, A.S., 2016, <doi:10.48550/arXiv.1511.01169>). Provides functions for easily creating R objects with partial_fit/predict methods from some given objective/gradient/predict functions. Includes an example stochastic logistic regression using these optimizers. Provides header files and registered C routines for using it directly from C/C++.

Version: 0.1.2-1
Published: 2021-09-26
DOI: 10.32614/CRAN.package.stochQN
Author: David Cortes
Maintainer: David Cortes <david.cortes.rivera at>
License: BSD_2_clause + file LICENSE
NeedsCompilation: yes
In views: Optimization
CRAN checks: stochQN results


Reference manual: stochQN.pdf


Package source: stochQN_0.1.2-1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): stochQN_0.1.2-1.tgz, r-oldrel (arm64): stochQN_0.1.2-1.tgz, r-release (x86_64): stochQN_0.1.2-1.tgz, r-oldrel (x86_64): stochQN_0.1.2-1.tgz
Old sources: stochQN archive


Please use the canonical form to link to this page.