Collapsing Taylor Mode Automatic Differentiation

Felix Dangel (Vector Institute, Toronto) · Marius Zeinhofer (Simula Research Laboratory) · Tim Siebert (Humboldt Universität Berlin) · Andrea Walther (Humboldt Universität zu Berlin)
accelerationautomatic differentiationcollapsing procedurecomputational efficiencycomputational graphforward laplacianlinear pde operatorsmachine learning compilernested backpropagationoptimization techniquepartial differential equationsperformance evaluationrandomized taylor modescientific machine learningtaylor mode

Computing partial differential equation (PDE) operators via nested backpropagation is expensive, yet popular, and severely restricts their utility for scientific machine learning. Recent advances, like the forward Laplacian and randomizing Taylor mode automatic differentiation (AD), propose forward schemes to address this. We introduce an optimization technique for Taylor mode that 'collapses' derivatives by rewriting the computational graph, and demonstrate how to apply it to general linear PDE operators, and randomized Taylor mode. The modifications simply require propagating a sum up the computational graph, which could