1 code implementation • 13 Jun 2023 • Gaurav Arya, Ruben Seyer, Frank Schäfer, Kartik Chandra, Alexander K. Lew, Mathieu Huot, Vikash K. Mansinghka, Jonathan Ragan-Kelley, Christopher Rackauckas, Moritz Schauer
We develop an algorithm for automatic differentiation of Metropolis-Hastings samplers, allowing us to differentiate through probabilistic inference, even if the model has discrete components within it.
Additionally, we address the question: is there a way to simultaneously achieve the robustness of implicit layers while allowing the reduced computational expense of an explicit layer?
Increasing emphasis on data and quantitative methods in the biomedical sciences is making biological research more computational.
While we can control the computational cost by choosing the number of layers in standard architectures, in NDEs the number of neural network evaluations for a forward pass can depend on the number of steps of the adaptive ODE solver.
We showcase how this can be used to optimize term construction and give a 113x acceleration on general symbolic transformations.
We first show the challenges of learning neural ODE in the classical stiff ODE systems of Robertson's problem and propose techniques to mitigate the challenges associated with scale separations in stiff systems.
no code implementations • 3 Nov 2020 • Emil Annevelink, Rachel Kurchin, Eric Muckley, Lance Kavalsky, Vinay I. Hegde, Valentin Sulzer, Shang Zhu, Jiankun Pu, David Farina, Matthew Johnson, Dhairya Gandhi, Adarsh Dave, Hongyi Lin, Alan Edelman, Bharath Ramsundar, James Saal, Christopher Rackauckas, Viral Shah, Bryce Meredig, Venkatasubramanian Viswanathan
Large-scale electrification is vital to addressing the climate crisis, but several scientific and technological challenges remain to fully electrify both the chemical industry and transportation.
In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets."
In this manuscript we investigate the performance characteristics of Discrete Local Sensitivity Analysis implemented via Automatic Differentiation (DSAAD) against continuous adjoint sensitivity analysis.
Performant numerical solving of differential equations is required for large-scale scientific modeling.
Software Engineering Mathematical Software