130 citations · 428 across the 6 of their papers we have counts for
Showing 2018Show all
3 papers · 1 filter
math.NA2018★ 18 cited
A Comparison of Automatic Differentiation and Continuous Sensitivity Analysis for Derivatives of Differential Equation Solutions
Yingbo Ma, Vaibhav Dixit, Mike Innes +2
Derivatives of differential equation solutions are commonly for parameter estimation, fitting neural differential equations, and as model diagnostics. However, with a litany of cho…
cs.PL2018★ 127 cited
Fashionable Modelling with Flux
Michael Innes, Elliot Saba, Keno Fischer +6
Machine learning as a discipline has seen an incredible surge of interest in recent years due in large part to a perfect storm of new theory, superior tooling, renewed interest in…
cs.PL2018★ 61 cited
Don't Unroll Adjoint: Differentiating SSA-Form Programs
Michael Innes
This paper presents reverse-mode algorithmic differentiation (AD) based on source code transformation, in particular of the Static Single Assignment (SSA) form used by modern compi…