#automaticdifferentiation — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #automaticdifferentiation, aggregated by home.social.
-
`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.`
https://arxiv.org/abs/2305.03863
#calculus #software #numericalAnalysis #automaticDifferentiation #uncertainty
-
New publication https://doi.org/10.1038/s41524-025-01880-3
Our work on AD-DFPT, a unification of #automaticdifferentiation with linear response for #densityfunctionaltheory is published in npj Computational Materials. We show examples for #property predition, #uncertainty propagation, the design of #materials and #machinelearning of new #dft models. #condensedmatter #dftk -
New publication https://doi.org/10.1038/s41524-025-01880-3
Our work on AD-DFPT, a unification of #automaticdifferentiation with linear response for #densityfunctionaltheory is published in npj Computational Materials. We show examples for #property predition, #uncertainty propagation, the design of #materials and #machinelearning of new #dft models. #condensedmatter #dftk -
New publication https://doi.org/10.1038/s41524-025-01880-3
Our work on AD-DFPT, a unification of #automaticdifferentiation with linear response for #densityfunctionaltheory is published in npj Computational Materials. We show examples for #property predition, #uncertainty propagation, the design of #materials and #machinelearning of new #dft models. #condensedmatter #dftk -
#SciML fact of the day: automatic differentiation fails to give the correct derivative on a lot of very simple functions 😱 😱 😱 . #julialang #automaticdifferentiation
-
Automatic Differentiation Can Be Incorrect
#HackerNews #AutomaticDifferentiation #Incorrectness #NumericalAnalysis #Simulation #MachineLearning
-
New preprint: https://arxiv.org/abs/2509.07785
We present an implementation of AD-DFPT, a unification of #automaticdifferentiation with classical #dfpt response techniques for #densityfunctionaltheory (#dft). We demonstrate its use for #property predition, #uncertainty propagation, design of new #materials as well as the #machinelearning of new #dft models.
#condensedmatter #planewave #response #physics #simulation #computation
-
An illustrated guide to automatic sparse differentiation
https://iclr-blogposts.github.io/2025/blog/sparse-autodiff/
#HackerNews #automaticdifferentiation #sparseautodiff #illustration #machinelearning #ICLR2025
-
Have you ever thought 💡 of using JAX as 🧮 #automaticdifferentiation engine in 💻 finite element simulations? Boost the performance 🏇 of computationally-expensive hyperelastic material models with #jit in 🔍 FElupe! 🚀 🚀
https://github.com/adtzlr/felupe
#python #jax #finiteelementmethod #scientificcomputing #computationalmechanics #fea #fem #hyperelasticity
-
This paper from @jenseisert and colleagues sounds interesting!
"The incorporation of automatic differentiation in tensor networks algorithms has ultimately enabled a new, flexible way for variational simulation of ground states and excited states. In this work, we review the state of the art of the variational iPEPS framework. We present and explain the functioning of an efficient, comprehensive and general tensor network library for the simulation of infinite two-dimensional systems using iPEPS, with support for flexible unit cells and different lattice geometries."
https://scirate.com/arxiv/2308.12358
#quantum #TensorNetwork #computational #physics #AutomaticDifferentiation #iPEPS
-
This paper from @jenseisert and colleagues sounds interesting!
"The incorporation of automatic differentiation in tensor networks algorithms has ultimately enabled a new, flexible way for variational simulation of ground states and excited states. In this work, we review the state of the art of the variational iPEPS framework. We present and explain the functioning of an efficient, comprehensive and general tensor network library for the simulation of infinite two-dimensional systems using iPEPS, with support for flexible unit cells and different lattice geometries."
https://scirate.com/arxiv/2308.12358
#quantum #TensorNetwork #computational #physics #AutomaticDifferentiation #iPEPS
-
I really enjoyed the talk by Manuel Drehwald at #RustSciComp23 who drew the lines of an exciting future for #AutomaticDifferentiation in #Rust with #LLVM #Enzyme , which should be directly integrated into the compiler at an horizon of a couple of months.
If I understood correctly, the idea is to differentiate code at the LLVM IR level, *after optimization* (and to do another pass of optimization after that). This can produce faster code than the AD engines that operate at the source code level.
-
I really enjoyed the talk by Manuel Drehwald at #RustSciComp23 who drew the lines of an exciting future for #AutomaticDifferentiation in #Rust with #LLVM #Enzyme , which should be directly integrated into the compiler at an horizon of a couple of months.
If I understood correctly, the idea is to differentiate code at the LLVM IR level, *after optimization* (and to do another pass of optimization after that). This can produce faster code than the AD engines that operate at the source code level.
-
I really enjoyed the talk by Manuel Drehwald at #RustSciComp23 who drew the lines of an exciting future for #AutomaticDifferentiation in #Rust with #LLVM #Enzyme , which should be directly integrated into the compiler at an horizon of a couple of months.
If I understood correctly, the idea is to differentiate code at the LLVM IR level, *after optimization* (and to do another pass of optimization after that). This can produce faster code than the AD engines that operate at the source code level.
-
I really enjoyed the talk by Manuel Drehwald at #RustSciComp23 who drew the lines of an exciting future for #AutomaticDifferentiation in #Rust with #LLVM #Enzyme , which should be directly integrated into the compiler at an horizon of a couple of months.
If I understood correctly, the idea is to differentiate code at the LLVM IR level, *after optimization* (and to do another pass of optimization after that). This can produce faster code than the AD engines that operate at the source code level.
-
I really enjoyed the talk by Manuel Drehwald at #RustSciComp23 who drew the lines of an exciting future for #AutomaticDifferentiation in #Rust with #LLVM #Enzyme , which should be directly integrated into the compiler at an horizon of a couple of months.
If I understood correctly, the idea is to differentiate code at the LLVM IR level, *after optimization* (and to do another pass of optimization after that). This can produce faster code than the AD engines that operate at the source code level.
-
#CFP for `Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators`, a workshop at #ICML
https://twitter.com/FHKPetersen/status/1657283011459821569
Differentiable programming is a powerful tool, so I am quite interested in this workshop (especially as a #JuliaLang user, which has fantastic #AD support).
-
Understanding and Implementing Automatic Differentiation
2022-12-04 :: racket, math, machine-learning, projects, tutorials
By: Mike Delmonaco#Racket #RacketLang #RacketLanguage #AI ##MachineLearning #AutomaticDifferentiation #tutorial
-
Call for Talk Proposals for the Enzyme (#AutomaticDifferentiation in #LLVM) Conference.
-
📺 I started a new video series on primitive rules for #automaticdifferentiation :https://www.youtube.com/watch?v=PwSaD50jTv8&list=PLISXH-iEM4Jn3SEi07q8MJmDD6BaMWlJE
starting at scalar rules, continuing with vector/array rules, and finally some results from using the implicit function theorem.Primitive rules build the basis for automatically differentiating through arbitrary computer programs.
New video to be released every three days :)
-
A consistently solid #JuliaLang YouTube Channel: https://youtube.com/c/MachineLearningSimulation
It mainly covers some advanced topics in one of the strongest areas of #Julia, #AutomaticDifferentiation, especially when applied to the scientific computing domain. For example: https://youtu.be/e4O6Z9o_D0k
Most topics also have a video covering it using #Jax or one of the specialized #PyTorch or #TensorFlow extensions (e.g., TensorFlow Distributions).