paper-with-me

Papers

Software-based Automatic Differentiation is Flawed

2023-05-05 · Daniel Johnson, Trevor Maxfield, Yongxu Jin, Ronald Fedkiw

Various software efforts embrace the idea that object oriented programming enables a convenient implementation of the chain rule, facilitating so-called automatic differentiation via backpropagation. Such frameworks have no mechanism for simplifying the expressions (obtained via the chain rule) before evaluating them. As we illustrate below, the resulting errors tend to be unbounded.

📄 PDF Abstract BibTeX arXiv:2305.03863

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

4D-Var using Hessian approximation and backpropagation applied to automatically-differentiable numerical and machine learning models

2024-08-05 · Kylen Solvik, Stephen G. Penny, Stephan Hoyer

Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) data assimilation is often difficult to implement in practice due to the need to develop and maintain a software-based…

TestLab: An Intelligent Automated Software Testing Framework

2023-06-06 · Tiago Dias, Arthur Batista, Eva Maia, Isabel Praça

The prevalence of software systems has become an integral part of modern-day living. Software usage has increased significantly, leading to its growth in both size and complexity. Consequently, software development is be…

software testing

Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming

2018-09-25 · NeurIPS 2018 12 · Bart van Merriënboer, Dan Moldovan, Alexander B. Wiltschko

The need to efficiently calculate first- and higher-order derivatives of increasingly complex models expressed in Python has stressed or exceeded the capabilities of available tools. In this work, we explore techniques f…

TreeFlow: probabilistic programming and automatic differentiation for phylogenetics

2022-11-09 · Christiaan Swanepoel, Mathieu Fourment, Xiang Ji, Hassan Nasif 외

Probabilistic programming frameworks are powerful tools for statistical modelling and inference. They are not immediately generalisable to phylogenetic problems due to the particular computational properties of the phylo…

Probabilistic Programming

Physics-informed Neural-Network Software for Molecular Dynamics Applications

2020-11-06 · Taufeq Mohammed Razakh, Beibei Wang, Shane Jackson, Rajiv K. Kalia 외

We have developed a novel differential equation solver software called PND based on the physics-informed neural network for molecular dynamics simulators. Based on automatic differentiation technique provided by Pytorch,…