antGLasso: An Efficient Tensor Graphical Lasso Algorithm

Bailey Andrew, David Westhead, Luisa Cutillo

Keywords: bigraphical lasso, network inference, gaussian graphical models

TL;DR: We propose a bigraphical lasso algorithm that is much faster than alternatives while maintaining state-of-the-art performance.

Abstract: The class of bigraphical lasso algorithms (and, more broadly, 'tensor'-graphical lasso algorithms) has been used to estimate dependency structures within matrix and tensor data. However, all current methods to do so take prohibitively long on modestly sized datasets. We present a novel tensor-graphical lasso algorithm that directly estimates the dependency structure, unlike its iterative predecessors. This provides a speedup of multiple orders of magnitude, allowing this class of algorithms to be used on large, real-world datasets.