Software Implementations

I develop and maintain software implementations (mainly in Python and R ) accompanying my research on Bayesian modeling, scalable inference, scientific machine learning, and the analysis of structured data.

pyJASPER

Python implementation of JASPER, a spatial basis function based count-regression framework for joint Bayesian analysis of spatial expression, for detecting spatially variable genes.

GitHub · Preprint

VaSST

Python implementation of VaSST, a variational inference method for symbolic regression using soft symbolic trees, designed for interpretable and uncertainty-aware equation discovery.

GitHub · Preprint

BayeSymX

Python implementation of BayeSym\(\mathbb{X}\), a probabilistic symbolic regression method using operator-induced and regularized symbolic forests for scientific equation discovery.

GitHub · Preprint

TAVIE-SSG

Python implementation of TAVIE-SSG, a scalable generalized tangent approximation based variational inference framework for strongly super-Gaussian likelihoods.

GitHub · Preprint

AMOGP

R implementation of AMO-GP, an additive nonparametric regression method with spatial and network-valued predictors, motivated by neuroimaging applications.

GitHub

dame-flame

Python package for DAME and FLAME: a family of fast and interpretable almost-matching-exactly methods for scalable and efficient causal inference.

PyPI · Paper

ODIN-python

Python implementation of ODIN, an outlier-detection method for populations of network-valued observations, motivated by applications in structural connectomics.

GitHub · Paper

ODIN-R

R implementation of ODIN, an outlier-detection method for populations of network-valued observations, motivated by applications in structural connectomics.

GitHub · Paper