{"id":1137,"date":"2026-07-24T17:05:34","date_gmt":"2026-07-24T17:05:34","guid":{"rendered":"https:\/\/sites.rutgers.edu\/nawaf-bou-rabee\/software\/"},"modified":"2026-09-11T20:14:14","modified_gmt":"2026-09-11T20:14:14","slug":"software","status":"publish","type":"page","link":"https:\/\/sites.rutgers.edu\/nawaf-bou-rabee\/software\/","title":{"rendered":"Software"},"content":{"rendered":"
\n

Open-source implementations, interactive demos, and reproducibility materials from my research on Markov chain Monte Carlo methods.<\/p>\n

walnutpie<\/h2>\n

WALNUTS, the Within-Orbit Adaptive Leapfrog No-U-Turn Sampler, adapts the leapfrog step size within<\/i> each trajectory, so one chain can follow a target whose scale changes from region to region. The reference implementation is walnutpie<\/b><\/a>, a Python package for Markov chain Monte Carlo sampling of differentiable target log densities, maintained at the Flatiron Institute. It takes models from Stan, PyMC, NumPyro, JAX and Numba, or a plain Python function that returns a log density and its gradient.<\/p>\n

pip install walnutpie<\/pre>\n
import walnutpie as wp\r\n\r\ndef logp(x):\r\n    # your code here\r\n    lp = ...\r\n    gradient = ...\r\n    return lp, gradient\r\n\r\ndraws = wp.walnuts_pyfunc(logp, num_params=10)\r\n\r\nprint(wp.ess(draws))<\/pre>\n
Documentation<\/a> · Source<\/a> · PyPI<\/a><\/p>\n
The core is a header-only C++ library whose only dependency is Eigen. CMake projects can depend on the walnutpie<\/code> target; otherwise add the include\/<\/code> directory to your include paths and provide Eigen separately. Code is released under the MIT license, documentation under CC-BY 4.0.<\/p>\n
How to cite<\/h2>\n
N. Bou-Rabee, B. Carpenter, T. S. Kleppe & S. Liu, The Within-Orbit Adaptive Leapfrog No-U-Turn Sampler<\/a>, Journal of Machine Learning Research, Vol. 27, No. 113, pp. 1-64, 2026.<\/p>\n
@article{JMLR:v27:25-1452,\r\n  author  = {Nawaf Bou-Rabee and Bob Carpenter and Tore Selland Kleppe and Sifan Liu},\r\n  title   = {The Within-Orbit Adaptive Leapfrog No-U-Turn Sampler},\r\n  journal = {Journal of Machine Learning Research},\r\n  year    = {2026},\r\n  volume  = {27},\r\n  number  = {113},\r\n  pages   = {1--64},\r\n  url     = {http:\/\/jmlr.org\/papers\/v27\/25-1452.html}\r\n}<\/pre>\n
Demonstrations and reproducibility<\/h2>\n