Robuta

https://www.sintef.no/en/publications/publication/10250606/ Advancing Turbomachinery Meanline Modeling and Optimization With Automatic Differentiation - SINTEF automatic differentiationadvancingturbomachinerymodelingoptimization https://openreview.net/forum?id=_b0jOHfZbfD An automatic differentiation system for the age of differential privacy | OpenReview Method for utilisation of sensitivity tracking for optimal noise calibration in DP automatic differentiationfor theage ofdifferential privacysystem https://arxiv.org/abs/1810.08297 [1810.08297] Dynamic Automatic Differentiation of GPU Broadcast Kernels Abstract page for arXiv paper 1810.08297: Dynamic Automatic Differentiation of GPU Broadcast Kernels automatic differentiation181008297dynamicgpu https://openreview.net/forum?id=SkxEF3FNPH Taylor-Mode Automatic Differentiation for Higher-Order Derivatives in JAX | OpenReview Generalizes forward-mode AD for higher-order derivatives, implements in JAX, applications to Neural ODEs. automatic differentiationtaylormode https://openreview.net/forum?id=uqg3FhRZaq On the complexity of nonsmooth automatic differentiation | OpenReview Backpropagation of nonsmooth gradients is proved to be a fast/cheap process for the vast class of locally Lipschitz semi-algebraic functions. on theautomatic differentiationcomplexityopenreview https://www.sintef.no/en/publications/publication/1957232/ Faster Simulation with Optimized Automatic Differentiation and Compiled Linear Solvers - SINTEF automatic differentiationfastersimulationoptimized https://openreview.net/forum?id=OQHrwtBXzs Physics-Informed Automatic Differentiation for Single-Shot Nanoscale 3D Imaging in In Situ... automatic differentiationsingle shot https://openreview.net/forum?id=WUMH5xloWn Automatic differentiation of nonsmooth iterative algorithms | OpenReview We describe the asymptotics of nonsmooth derivatives obtained by automatic differentiation of fixed point algorithms and show that they converge to classical... automatic differentiationiterativealgorithmsopenreview https://www.cambridge.org/core/journals/journal-of-functional-programming/article/perturbation-confusion-in-forward-automatic-differentiation-of-higherorder-functions/A808189A3875A2EDAC6E0D62CF2AD262 Perturbation confusion in forward automatic differentiation of higher-order functions | Journal of... Perturbation confusion in forward automatic differentiation of higher-order functions - Volume 29 higher order functionsautomatic differentiationperturbationconfusionforward https://hashnode.com/posts/forward-mode-automatic-differentiation-go-dual-numbers/67c46727f14451763c225890 Discussion on "Forward Mode Automatic Differentiation in Go: A Practical Guide with Dual Numbers" |... Discussion on "Forward Mode Automatic Differentiation in Go: A Practical Guide with Dual Numbers". Differentiation is at the heart of calculus, telling us the... https://openreview.net/forum?id=GtXSN52nIW Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation |... From implicit differentiation to probabilistic modeling, Jacobian and Hessian matrices have many potential use cases in Machine Learning (ML), but they are... sparserbetterfasterstrongersparsity https://openreview.net/forum?id=ykZibuSbJj An Illustrated Guide to Automatic Sparse Differentiation | OpenReview In numerous applications of machine learning, Hessians and Jacobians exhibit sparsity, a property that can be leveraged to vastly accelerate their computation.... illustrated guideautomaticsparsedifferentiationopenreview https://www.jmlr.org/papers/v27/25-1024.html A Common Interface for Automatic Differentiation common interfaceautomaticdifferentiation https://uwaterloo.ca/applied-mathematics/events/masters-defense-zhou-structured-reverse-mode-automatic Master's Defense | An Zhou, Structured Reverse Mode Automatic Differentiation in Nested Monte Carlo... https://informaconnect.com/a-brief-introduction-to-automatic-adjoint-differentiation-aad/ A brief introduction to Automatic Adjoint Differentiation (AAD) AAD is both a simple but somewhat hard to comprehend mathematical algorithm, and a highly challenging computer programming practice. Antoine Savine breaks it... a brief introductionautomaticadjointdifferentiationaad https://openreview.net/forum?id=NVvUkYNYPK Are gradients worth the effort? Comparing automatic differentiation and simulation-based inference... Agent-based models (ABMs) are flexible tools for simulating complex systems, but their calibration is difficult because their likelihoods are intractable and... worth the effort