mlsanityData to 7 Oct 2026

Differentiable Physics: A Position Piece

arXiv 2109.07573 ↗First posted 14 Sep 2021cs.LG physics.chem-phcited by 12

Not on the map. Why?

Abstract (arXiv)

Differentiable physics provides a new approach for modeling and understanding the physical systems by pairing the new technology of differentiable programming with classical numerical methods for physical simulation. We survey the rapidly growing literature of differentiable physics techniques and highlight methods for parameter estimation, learning representations, solving differential equations, and developing what we call scientific foundation models using data and inductive priors. We argue that differentiable physics offers a new paradigm for modeling physical phenomena by combining classical analytic solutions with numerical methodology using the bridge of differentiable programming.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 57 of its 123 references that are in the map. First posted on arXiv 14 Sep 2021.

Builds on

57 of 123 references.

References · 57

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  7. 2018Neural Ordinary Differential Equationscited by 3,733
  8. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  9. 2016Group Equivariant Convolutional Networkscited by 1,154
  10. 2015Automatic differentiation in machine learning: a surveycited by 846
  11. 2019Hamiltonian Neural Networkscited by 702
  12. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
38 more
  1. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  2. 2020Directional Message Passing for Molecular Graphscited by 556
  3. 2017Solving high-dimensional partial differential equations using deep learningcited by 549
  4. 2021Machine learning accelerated computational fluid dynamicscited by 461
  5. 2020Lagrangian Neural Networkscited by 388
  6. 2020Universal Differential Equations for Scientific Machine Learningcited by 345
  7. 2020Multipole Graph Neural Operator for Parametric Partial Differential Equationscited by 343
  8. 2020Power of data in quantum machine learningcited by 336
  9. 2020ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Predictioncited by 332
  10. 2019Tackling Climate Change with Machine Learningcited by 264
  11. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  12. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 248
  13. 2020The large learning rate phase of deep learning: the catapult mechanismcited by 206
  14. 2019Ab-Initio Solution of the Many-Electron Schr"odinger Equation with Deep Neural Networkscited by 195
  15. 2021The Principles of Deep Learning Theorycited by 169
  16. 2018Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Networkcited by 168
  17. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 168
  18. 2020Multiscale Deep Equilibrium Modelscited by 149
  19. 2019Flow-based generative models for Markov chain Monte Carlo in lattice field theorycited by 147
  20. 2019The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectivescited by 139
  21. 2020Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Predictioncited by 137
  22. 2019Deep neural network solution of the electronic Schr"odinger equationcited by 124
  23. 2019Machine learning for molecular simulationcited by 109
  24. 2020Equivariant flow-based sampling for lattice gauge theorycited by 102
  25. 2020Sampling using SU(N) gauge equivariant flowscited by 83
  26. 2017DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamicscited by 79
  27. 2018Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profilescited by 55
  28. 2019Learning to learn with quantum neural networks via classical neural networkscited by 55
  29. 2018PotentialNet for Molecular Property Predictioncited by 46
  30. 2021Simulating Continuum Mechanics with Multi-Scale Graph Neural Networkscited by 39
  31. 2020Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physicscited by 36
  32. 2016Supervised Learning with Quantum-Inspired Tensor Networkscited by 35
  33. 2020Active learning of deep surrogates for PDEs: Application to metasurface designcited by 28
  34. 2018Dreaming neural networks: forgetting spurious memories and reinforcing pure onescited by 15
  35. 2020Machine learning on DNA-encoded libraries: A new paradigm for hit-findingcited by 15
  36. 2020DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theorycited by 15
  37. 2020Data-Driven Discovery of Coarse-Grained Equationscited by 14
  38. 2019Neural networks with redundant representation: detecting the undetectablecited by 12

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 6; 2025: 1; 2026: 2.

12 papers.

  1. 2024Scaling physics-informed hard constraints with mixture-of-expertscited by 24
  2. 2022Differentiable physics-enabled closure modeling for Burgers' turbulencecited by 7
  3. 2024What You See is Not What You Get: Neural Partial Differential Equations and The Illusion of Learningcited by 5
  4. 2023Open Source Infrastructure for Differentiable Density Functional Theorycited by 1
  5. 2024Modern, Efficient, and Differentiable Transport Equation Models using JAX: Applications to Population Balance Equationscited by 1
  6. 2022Differentiable Physics-based Greenhouse Simulationcited by 0
  7. 2024Open-Source Fermionic Neural Networks with Ionic Charge Initializationcited by 0
  8. 2024Open source Differentiable ODE Solving Infrastructurecited by 0
  9. 2024Finding the Underlying Viscoelastic Constitutive Equation via Universal Differential Equations and Differentiable Physicscited by 0
  10. 2025Learning second-order TVD flux limiters using differentiable solverscited by 0
  11. 2026Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programmingcited by 0
  12. 2026Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networkscited by 0