A Common Interface for Automatic Differentiation
By: Guillaume Dalle, Adrian Hill
Potential Business Impact:
Lets scientists easily test different math tools.
For scientific machine learning tasks with a lot of custom code, picking the right Automatic Differentiation (AD) system matters. Our Julia package DifferentiationInterface$.$jl provides a common frontend to a dozen AD backends, unlocking easy comparison and modular development. In particular, its built-in preparation mechanism leverages the strengths of each backend by amortizing one-time computations. This is key to enabling sophisticated features like sparsity handling without putting additional burdens on the user.
Similar Papers
DaCe AD: Unifying High-Performance Automatic Differentiation for Machine Learning and Scientific Computing
Machine Learning (CS)
Makes computers learn faster without changing code.
A General and Streamlined Differentiable Optimization Framework
Machine Learning (CS)
Lets computers learn from complex decisions.
Scalable Analysis and Design Using Automatic Differentiation
Numerical Analysis
Makes computer simulations of complex problems faster.