pith. sign in

arxiv: 2603.12676 · v2 · pith:D2B5SZ6Mnew · submitted 2026-03-13 · 💻 cs.LG

Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs

Zhangyong Liang This is my paper

Pith reviewed 2026-05-21 11:33 UTC · model grok-4.3

classification 💻 cs.LG
keywords parameterized PDEslatent dynamicsNeural ODEmanifold fusiongeneralizationtemporal extrapolationphysics-informed neural networks
0
0 comments X

The pith

Modeling PDE prediction as latent dynamic evolution separates parameter changes from time progression.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes a framework that treats the solution of parameterized partial differential equations as the evolution of a latent state rather than fitting coordinates directly. Parameters are mapped by a feed-forward network to a latent embedding that starts and conditions a Neural ODE, which then evolves the state over time. A shared decoder fuses this evolving state with spatial coordinates and parameters to reconstruct the solution. This separation is meant to reduce conflicts between varying the parameters and advancing in time, leading to smoother manifolds and better performance on new parameters and extended time periods. A sympathetic reader would care because many scientific simulations require exploring different physical settings and predicting further into the future without retraining the model each time.

Core claim

DLDMF explicitly separates space, time, and parameters by mapping PDE parameters directly to a continuous latent embedding through a feed-forward network. This embedding initializes and conditions a parameter-conditioned Neural ODE. A dynamic manifold fusion mechanism uses a shared decoder to combine spatial coordinates, parameter embeddings, and time-evolving latent states to reconstruct the spatiotemporal solution. By modeling prediction as latent dynamic evolution rather than static coordinate fitting, the approach reduces interference between parameter variation and temporal evolution while preserving a smooth and coherent solution manifold.

What carries the argument

The parameter-conditioned Neural ODE initialized by a feed-forward mapped latent embedding, combined with dynamic manifold fusion via a shared decoder.

If this is right

  • Performs well on unseen parameter settings without retraining.
  • Achieves long-term temporal extrapolation beyond the training time range.
  • Outperforms state-of-the-art baselines in accuracy on benchmark problems.
  • Maintains a smooth and coherent solution manifold across parameter variations.
  • Reduces interference between parameter changes and time evolution in the model.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This separation might allow the same latent dynamics to apply to a wider range of physical systems by adjusting only the initial embedding.
  • Future work could test if this approach scales to higher-dimensional or nonlinear PDEs with many parameters.
  • It suggests that enforcing disentanglement in latent space could improve generalization in other time-dependent modeling tasks like fluid dynamics or climate simulation.

Load-bearing premise

A feed-forward network can map any PDE parameters to a latent embedding that allows a Neural ODE to evolve the solution stably without needing to decode the parameters again during testing or causing jumps in the solution space.

What would settle it

Running the model on a parameter value outside the training range and checking if the predicted solution matches the true PDE solution over an extended time period beyond training data; failure would show the mapping or evolution does not generalize.

Figures

Figures reproduced from arXiv: 2603.12676 by Zhangyong Liang.

Figure 1
Figure 1. Figure 1: Physics-informed neural PDE solvers. Colorful squares denote spatial ( [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Comparison of ground truth (solid black) and P [PITH_FULL_IMAGE:figures/full_fig_p016_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Growth of P2 INN’s L2 relative error over the time horizon T. Latent space dynamic of parameterized PDEs may exist. Solutions under nearby PDE parameters often share common structures, suggesting that their evolution trajectories may lie on a low-dimensional manifold [26, 21]. Latent dynamics models show that continuous-time evolution can be captured efficiently by learning a latent ODE and decoding latent… view at source ↗
Figure 4
Figure 4. Figure 4: P2 INN’s error metrics versus time horizon T. (a) L2 absolute error, (b) L2 relative error, (c) maximum error grow approximately linearly beyond the training limit; (d) explained variance decreases approximately linearly. tions can be interpreted as modulating amplitudes and phases of wave com￾ponents, which can be beneficial for representing oscillatory signals [14, 41]. However, directly factorizing time… view at source ↗
read the original abstract

Generalizing neural surrogate models across different PDE parameters remains difficult because changes in PDE coefficients often make learning harder and optimization less stable. The problem becomes even more severe when the model must also predict beyond the training time range. Existing methods usually cannot handle parameter generalization and temporal extrapolation at the same time. Standard parameterized models treat time as just another input and therefore fail to capture intrinsic dynamics, while recent continuous-time latent methods often rely on expensive test-time auto-decoding for each instance, which is inefficient and can disrupt continuity across the parameterized solution space. To address this, we propose Disentangled Latent Dynamics Manifold Fusion (DLDMF), a physics-informed framework that explicitly separates space, time, and parameters. Instead of unstable auto-decoding, DLDMF maps PDE parameters directly to a continuous latent embedding through a feed-forward network. This embedding initializes and conditions a latent state whose evolution is governed by a parameter-conditioned Neural ODE. We further introduce a dynamic manifold fusion mechanism that uses a shared decoder to combine spatial coordinates, parameter embeddings, and time-evolving latent states to reconstruct the corresponding spatiotemporal solution. By modeling prediction as latent dynamic evolution rather than static coordinate fitting, DLDMF reduces interference between parameter variation and temporal evolution while preserving a smooth and coherent solution manifold. As a result, it performs well on unseen parameter settings and in long-term temporal extrapolation. Experiments on several benchmark problems show that DLDMF consistently outperforms state-of-the-art baselines in accuracy, parameter generalization, and extrapolation robustness.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper proposes Disentangled Latent Dynamics Manifold Fusion (DLDMF), a physics-informed neural framework for solving parameterized PDEs. It explicitly disentangles space, time, and parameters by using a feed-forward network to map PDE parameters directly to a continuous latent embedding; this embedding initializes and conditions a parameter-conditioned Neural ODE whose evolution is decoded via a dynamic manifold fusion mechanism with a shared decoder that combines spatial coordinates, parameter embeddings, and time-evolving latent states. The central claim is that modeling prediction as latent dynamic evolution (rather than static fitting) reduces interference between parameter variation and temporal dynamics, preserves a smooth solution manifold, and yields improved accuracy, generalization to unseen parameters, and long-term temporal extrapolation on benchmark problems relative to state-of-the-art baselines.

Significance. If the empirical results and stability assumptions hold, the work could advance neural surrogates for parameterized PDEs by eliminating test-time auto-decoding while jointly addressing parameter generalization and temporal extrapolation. The explicit disentanglement via Neural ODEs and manifold fusion provides a concrete architectural template that may transfer to other scientific machine-learning tasks involving multi-scale physical systems.

major comments (2)
  1. [Method (parameter-to-latent mapping and Neural ODE conditioning)] The central architectural claim—that a feed-forward network produces a latent embedding that both initializes and stably conditions a parameter-conditioned Neural ODE across the solution manifold—lacks any explicit continuity enforcement (e.g., Lipschitz regularization, manifold penalties, or Jacobian constraints). This assumption is load-bearing for the generalization and long-term extrapolation results; without it, small parameter perturbations can induce divergent latent dynamics under integration.
  2. [Abstract and Experiments] The abstract asserts that 'experiments on several benchmark problems show that DLDMF consistently outperforms state-of-the-art baselines,' yet the provided text contains no quantitative error metrics, error bars, dataset specifications (number of parameter settings, time horizons, grid resolutions), or ablation studies isolating the dynamic manifold fusion component. These details are required to substantiate the central performance claims.
minor comments (1)
  1. [Method] The notation for the latent state z(t), parameter embedding e_p, and the fusion decoder could be formalized with explicit equations and a schematic diagram to clarify the information flow between the feed-forward mapper, Neural ODE, and shared decoder.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. We address each major comment point by point below, indicating where revisions will be made to strengthen the presentation and claims.

read point-by-point responses

  1. Referee: [Method (parameter-to-latent mapping and Neural ODE conditioning)] The central architectural claim—that a feed-forward network produces a latent embedding that both initializes and stably conditions a parameter-conditioned Neural ODE across the solution manifold—lacks any explicit continuity enforcement (e.g., Lipschitz regularization, manifold penalties, or Jacobian constraints). This assumption is load-bearing for the generalization and long-term extrapolation results; without it, small parameter perturbations can induce divergent latent dynamics under integration.

    Authors: We appreciate this observation regarding the need for explicit continuity enforcement. The feed-forward network with standard smooth activations (such as tanh) is continuous by construction, and the Neural ODE integration inherently produces continuous trajectories in latent space. However, we acknowledge that the original submission did not include explicit regularization such as Lipschitz constraints or manifold penalties on the parameter-to-latent mapping. To directly address the concern about stability under small parameter perturbations, we will incorporate a Lipschitz regularization term on the parameter embedding network in the revised manuscript. This term will be added to the overall loss function, with corresponding discussion in the method section and updated experimental protocols to verify its effect on generalization and extrapolation. revision: yes

  2. Referee: [Abstract and Experiments] The abstract asserts that 'experiments on several benchmark problems show that DLDMF consistently outperforms state-of-the-art baselines,' yet the provided text contains no quantitative error metrics, error bars, dataset specifications (number of parameter settings, time horizons, grid resolutions), or ablation studies isolating the dynamic manifold fusion component. These details are required to substantiate the central performance claims.

    Authors: We agree that the abstract would be strengthened by including concise quantitative support for the performance claims. While the full manuscript's Experiments section already reports relative L2 errors with standard deviations across multiple runs, specific dataset details (including the number of parameter settings, time horizons, and grid resolutions), and ablation studies on the dynamic manifold fusion component, these were not summarized in the abstract. We will revise the abstract to incorporate key quantitative metrics, error bar information, and brief references to the dataset specifications and ablations, ensuring the central claims are substantiated at the summary level without exceeding length constraints. revision: yes

Circularity Check

0 steps flagged

No circularity: DLDMF is an independent architectural proposal with no self-referential reductions

full rationale

The paper introduces DLDMF as a new framework that uses a feed-forward network to map PDE parameters to a latent embedding which initializes a parameter-conditioned Neural ODE, combined with a dynamic manifold fusion decoder. No equations, predictions, or core claims reduce by construction to fitted inputs, self-citations, or renamed known results. The derivation relies on the proposed separation of space/time/parameters and experimental validation on benchmarks rather than tautological definitions or load-bearing self-references. This is self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

2 free parameters · 1 axioms · 1 invented entities

The framework rests on the premise that space, time, and parameters can be usefully disentangled in a latent space whose dynamics are governed by a Neural ODE; several architectural choices function as free parameters whose values are not derived from first principles.

free parameters (2)
  • latent embedding dimension
    Hyperparameter size of the continuous latent state that is initialized from parameters and evolved by the Neural ODE.
  • Neural ODE integration tolerances and step size
    Numerical settings that control how the latent dynamics are integrated over time.
axioms (1)
  • domain assumption PDE solutions lie on a smooth manifold that can be factored into independent spatial, temporal, and parametric components in latent space.
    Invoked when the method separates the three factors and uses a shared decoder to recombine them.
invented entities (1)
  • dynamic manifold fusion mechanism no independent evidence
    purpose: Combines spatial coordinates, parameter embeddings, and evolving latent states inside a shared decoder to produce the solution field.
    New architectural component introduced to enforce coherence across the parameterized solution space.

pith-pipeline@v0.9.0 · 5793 in / 1401 out tokens · 38597 ms · 2026-05-21T11:33:48.858343+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

62 extracted references · 62 canonical work pages · 3 internal anchors

  1. [1]

    In12th USENIX symposium on operating systems design and implementation (OSDI 16), pages 265–283, 2016

    Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al.{TensorFlow}: A system for{Large-Scale}machine learning. In12th USENIX symposium on operating systems design and implementation (OSDI 16), pages 265–283, 2016

    work page 2016

  2. [2]

    Learning Dynamical Systems from Partial Observations

    IbrahimAyed, EmmanueldeBézenac, ArthurPajot, JulienBrajard, and PatrickGallinari. Learningdynamicalsystemsfrompartialobservations. arXiv preprint arXiv:1902.11136, 2019

    work page internal anchor Pith review Pith/arXiv arXiv 1902

  3. [3]

    Workshop report on basic research needs for scientific machine learning: Core technologies for artificial intelligence

    Nathan Baker, Frank Alexander, Timo Bremer, Aric Hagberg, Yannis Kevrekidis, HabibNajm, ManishParashar, AbaniPatra, JamesSethian, Stefan Wild, et al. Workshop report on basic research needs for scientific machine learning: Core technologies for artificial intelligence. Technical report, USDOE Office of Science (SC), Washington, DC (United States), 2019

    work page 2019

  4. [4]

    Relational inductive biases, deep learning, and graph networks

    Peter W Battaglia, Jessica B Hamrick, Victor Bapst, Alvaro Sanchez- Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, et al. Relational in- ductive biases, deep learning, and graph networks.arXiv preprint arXiv:1806.01261, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  5. [5]

    Automaticdifferentiationinmachinelearning: a survey.Journal of Marchine Learning Research, 18:1–43, 2018

    Atilim Gunes Baydin, Barak A Pearlmutter, Alexey Andreyevich Radul, andJeffreyMarkSiskind. Automaticdifferentiationinmachinelearning: a survey.Journal of Marchine Learning Research, 18:1–43, 2018

    work page 2018

  6. [6]

    Message passing neural pde solvers

    Johannes Brandstetter, Daniel E Worrall, and Max Welling. Message passing neural pde solvers. InInternational Conference on Learning Representations, 2021

    work page 2021

  7. [7]

    NeRV: Neural representations for videos

    Hao Chen, Bo He, Hanyu Wang, Yixuan Ren, Ser Nam Lim, and Abhinav Shrivastava. NeRV: Neural representations for videos. In Marc’Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy Liang, and Jenn Wortman Vaughan, editors,Advances in Neural Information Processing Systems, volume 34, pages 21557–21568. Curran Associates, Inc., 2021. 31

    work page 2021

  8. [8]

    Chiaramonte, Kevin Thomas Carlberg, and Eitan Grinspun

    Peter Yichen Chen, Jinxu Xiang, Dong Heon Cho, Yue Chang, G A Per- shing, Henrique Teles Maia, Maurizio M. Chiaramonte, Kevin Thomas Carlberg, and Eitan Grinspun. CROM: Continuous reduced-order mod- eling of PDEs using implicit neural representations. InInternational Conference on Learning Representations, 2023

    work page 2023

  9. [9]

    Neural ordinary differential equations.Advances in Neural Information Processing Systems, 31, 2018

    Ricky TQ Chen, Yulia Rubanova, Jesse Bettencourt, and David K Du- venaud. Neural ordinary differential equations.Advances in Neural Information Processing Systems, 31, 2018

    work page 2018

  10. [10]

    Parameterized physics- informed neural networks for parameterized pdes.arXiv preprint arXiv:2408.09446, 2024

    Woojin Cho, Minju Jo, Haksoo Lim, Kookjin Lee, Dongeun Lee, Sanghyun Hong, and Noseong Park. Parameterized physics- informed neural networks for parameterized pdes.arXiv preprint arXiv:2408.09446, 2024

    work page arXiv 2024

  11. [11]

    Lagrangian neural networks

    Miles Cranmer, Sam Greydanus, Stephan Hoyer, Peter Battaglia, David Spergel, and Shirley Ho. Lagrangian neural networks. InICLR 2020 Workshop, 2020

    work page 2020

  12. [12]

    Lagrangian neural networks, 2020

    Miles Cranmer, Sam Greydanus, Stephan Hoyer, Peter Battaglia, David Spergel, and Shirley Ho. Lagrangian neural networks, 2020

    work page 2020

  13. [13]

    Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami, Danilo Jimenez Rezende, and Dan Rosenbaum. From data to functa: Your data point is a function and you can treat it like one. In39th International Conference on Machine Learning (ICML), 2022

    work page 2022

  14. [14]

    Multiplicative filter networks

    Rizal Fathony, Anit Kumar Sahu, Devin Willmott, and J Zico Kolter. Multiplicative filter networks. InInternational Conference on Learning Representations, 2020

    work page 2020

  15. [15]

    Deep learning-based reduced order models in cardiac electrophysiology

    Stefania Fresca, Andrea Manzoni, Luca Dedè, and Alfio Quarteroni. Deep learning-based reduced order models in cardiac electrophysiology. PLoS ONE, 15(10), October 2020

    work page 2020

  16. [16]

    Deep learning-based reduced order models in cardiac electrophysiology

    Stefania Fresca, Andrea Manzoni, Luca Dedè, and Alfio Quarteroni. Deep learning-based reduced order models in cardiac electrophysiology. PLoS ONE, 15(10), October 2020. 32

    work page 2020

  17. [17]

    Yihang Gao, Ka Chun Cheung, and Michael K. Ng. Svd-pinns: Transfer learning of physics-informed neural networks via singular value decom- position. In2022 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, December 2022

    work page 2022

  18. [18]

    E(n) equivariant graph neural networks

    Víctor Garcia Satorras, Emiel Hoogeboom, and Max Welling. E(n) equivariant graph neural networks. InProceedings of the 38th Interna- tional Conference on Machine Learning, volume 139 ofProceedings of Machine Learning Research, pages 9323–9332. PMLR, 2021

    work page 2021

  19. [19]

    Learning to optimize multigrid pde solvers

    Daniel Greenfeld, Meirav Galun, Ronen Basri, Irad Yavneh, and Ron Kimmel. Learning to optimize multigrid pde solvers. InInternational Conference on Machine Learning, pages 2415–2423. PMLR, 2019

    work page 2019

  20. [20]

    Hamiltonian neural networks.Advances in Neural Information Processing Systems, 32:15379–15389, 2019

    Samuel Greydanus, Misko Dzamba, and Jason Yosinski. Hamiltonian neural networks.Advances in Neural Information Processing Systems, 32:15379–15389, 2019

    work page 2019

  21. [21]

    Meta-auto- decoder for solving parametric partial differential equations.Advances in Neural Information Processing Systems, 35:23426–23438, 2022

    Xiang Huang, Zhanhong Ye, Hongsheng Liu, Shi Ji, Zidong Wang, Kang Yang, Yang Li, Min Wang, Haotian Chu, Fan Yu, et al. Meta-auto- decoder for solving parametric partial differential equations.Advances in Neural Information Processing Systems, 35:23426–23438, 2022

    work page 2022

  22. [22]

    Ameya D Jagtap and George Em Karniadakis. Extended physics- informed neural networks (xpinns): A generalized space-time domain decomposition based deep learning framework for nonlinear partial differential equations.Communications in Computational Physics, 28(5):2002–2041, 2020

    work page 2002

  23. [23]

    Ameya D Jagtap, Ehsan Kharazmi, and George Em Karniadakis. Con- servative physics-informed neural networks on discrete domains for con- servation laws: Applications to forward and inverse problems.Computer Methods in Applied Mechanics and Engineering, 365:113028, 2020

    work page 2020

  24. [24]

    Physics-informed machine learning.Nature Reviews Physics, 3(6):422–440, 2021

    George Em Karniadakis, Ioannis G Kevrekidis, Lu Lu, Paris Perdikaris, Sifan Wang, and Liu Yang. Physics-informed machine learning.Nature Reviews Physics, 3(6):422–440, 2021

    work page 2021

  25. [25]

    Multi-task learning using uncertaintytoweighlossesforscenegeometryandsemantics

    Alex Kendall, Yarin Gal, and Roberto Cipolla. Multi-task learning using uncertaintytoweighlossesforscenegeometryandsemantics. InProceed- 33 ings of the IEEE conference on computer vision and pattern recognition, pages 7482–7491, 2018

    work page 2018

  26. [26]

    Characterizing possible failure modes in physics- informed neural networks.Advances in Neural Information Processing Systems, 34, 2021

    Aditi Krishnapriyan, Amir Gholami, Shandian Zhe, Robert Kirby, and Michael W Mahoney. Characterizing possible failure modes in physics- informed neural networks.Advances in Neural Information Processing Systems, 34, 2021

    work page 2021

  27. [27]

    Nonlinear reconstruction for operator learning of pdes with discontinuities

    Samuel Lanthaler, Roberto Molinaro, Patrik Hadorn, and Siddhartha Mishra. Nonlinear reconstruction for operator learning of pdes with discontinuities. InThe Eleventh International Conference on Learning Representations, 2022

    work page 2022

  28. [28]

    Deep conservation: A latent- dynamics model for exact satisfaction of physical conservation laws

    Kookjin Lee and Kevin T Carlberg. Deep conservation: A latent- dynamics model for exact satisfaction of physical conservation laws. InProceedings of the AAAI Conference on Artificial Intelligence, vol- ume 35, pages 277–285, 2021

    work page 2021

  29. [29]

    Machine learning struc- ture preserving brackets for forecasting irreversible processes.Advances in Neural Information Processing Systems, 34, 2021

    Kookjin Lee, Nathaniel Trask, and Panos Stinis. Machine learning struc- ture preserving brackets for forecasting irreversible processes.Advances in Neural Information Processing Systems, 34, 2021

    work page 2021

  30. [30]

    Adaptive finite element methods: A review.Applied Mechanics Reviews, 50(10):581–591, 1997

    Long Yuan Li and Peter Bettess. Adaptive finite element methods: A review.Applied Mechanics Reviews, 50(10):581–591, 1997

    work page 1997

  31. [31]

    Fourier neural operator for parametric partial differential equations

    Zongyi Li, Nikola Borislavov Kovachki, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar, et al. Fourier neural operator for parametric partial differential equations. In International Conference on Learning Representations, 2020

    work page 2020

  32. [32]

    A novel meta-learning initialization method for physics-informed neural networks.Neural Computing and Applications, pages 1–24, 2022

    Xu Liu, Xiaoya Zhang, Wei Peng, Weien Zhou, and Wen Yao. A novel meta-learning initialization method for physics-informed neural networks.Neural Computing and Applications, pages 1–24, 2022

    work page 2022

  33. [33]

    Learning nonlinear operators via deeponet based on the universal approximation theorem of operators.Nature machine intelli- gence, 3(3):218–229, 2021

    Lu Lu, Pengzhan Jin, Guofei Pang, Zhongqiang Zhang, and George Em Karniadakis. Learning nonlinear operators via deeponet based on the universal approximation theorem of operators.Nature machine intelli- gence, 3(3):218–229, 2021. 34

    work page 2021

  34. [34]

    Deep lagrangian net- works: Using physics as model prior for deep learning

    Michael Lutter, Christian Ritter, and Jan Peters. Deep lagrangian net- works: Using physics as model prior for deep learning. InInternational Conference on Learning Representations, 2018

    work page 2018

  35. [35]

    Olver.Introduction to partial differential equations

    Peter J. Olver.Introduction to partial differential equations. Undergrad- uate Texts in Mathematics. Springer Cham, 2014

    work page 2014

  36. [36]

    Deepsdf: Learning continuous signed distance functions for shape representation

    Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. Deepsdf: Learning continuous signed distance functions for shape representation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 165–174, 2019

    work page 2019

  37. [37]

    DeepSDF: Learning continuous signed distance functions for shape representation

    Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. DeepSDF: Learning continuous signed distance functions for shape representation. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 165–174, June 2019

    work page 2019

  38. [38]

    PyTorch: An imperative style, high-performance deep learning library.Advances in neural information processing sys- tems, 32, 2019

    Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Brad- bury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. PyTorch: An imperative style, high-performance deep learning library.Advances in neural information processing sys- tems, 32, 2019

    work page 2019

  39. [39]

    Nonstandard finite difference methods: recent trends and further developments.Journal of Difference Equations and Appli- cations, 22(6):817–849, 2016

    Kailash C Patidar. Nonstandard finite difference methods: recent trends and further developments.Journal of Difference Equations and Appli- cations, 22(6):817–849, 2016

    work page 2016

  40. [40]

    Snode: Spectral discretization of neural odes for system identification

    Alessio Quaglino, Marco Gallieri, Jonathan Masci, and Jan Koutník. Snode: Spectral discretization of neural odes for system identification. InInternational Conference on Learning Representations, 2019

    work page 2019

  41. [41]

    On thespec- tral bias of neural networks

    Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, FredHamprecht, Yoshua Bengio, and AaronCourville. On thespec- tral bias of neural networks. InInternational Conference on Machine Learning, pages 5301–5310. PMLR, 2019

    work page 2019

  42. [42]

    Maziar Raissi, Paris Perdikaris, and George E Karniadakis. Physics- informed neural networks: A deep learning framework for solving for- ward and inverse problems involving nonlinear partial differential equa- tions.Journal of Computational Physics, 378:686–707, 2019. 35

    work page 2019

  43. [43]

    Aconstrainedintegration(cint)approach to solving partial differential equations using artificial neural networks

    KeithRuddandSilviaFerrari. Aconstrainedintegration(cint)approach to solving partial differential equations using artificial neural networks. Neurocomputing, 155:277–285, 2015

    work page 2015

  44. [44]

    An Overview of Multi-Task Learning in Deep Neural Networks

    Sebastian Ruder. An overview of multi-task learning in deep neural networks.arXiv preprint arXiv:1706.05098, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  45. [45]

    Physics-informed neural ode (pinode): embedding physics into models using collocation points.Scientific Reports, 13(1):10166, 2023

    Aleksei Sholokhov, Yuying Liu, Hassan Mansour, and Saleh Nabi. Physics-informed neural ode (pinode): embedding physics into models using collocation points.Scientific Reports, 13(1):10166, 2023

    work page 2023

  46. [46]

    Paral- lel physics-informed neural networks via domain decomposition.Journal of Computational Physics, 447:110683, 2021

    Khemraj Shukla, Ameya D Jagtap, and George Em Karniadakis. Paral- lel physics-informed neural networks via domain decomposition.Journal of Computational Physics, 447:110683, 2021

    work page 2021

  47. [47]

    Implicit neural representations with periodic activation functions.Advances in Neural Information Processing Sys- tems, 33:7462–7473, 2020

    Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. Implicit neural representations with periodic activation functions.Advances in Neural Information Processing Sys- tems, 33:7462–7473, 2020

    work page 2020

  48. [48]

    StyleGAN-V: A continuous video generator with the price, image qual- ity and perks of StyleGAN2

    Ivan Skorokhodov, Sergey Tulyakov, and Mohamed Elhoseiny. StyleGAN-V: A continuous video generator with the price, image qual- ity and perks of StyleGAN2. InIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3626–3636, June 2022

    work page 2022

  49. [49]

    Infinite to finite: an overview of finite element analysis.Indian Journal of Dental Research, 21(3):425, 2010

    A Srirekha, Kusum Bashetty, et al. Infinite to finite: an overview of finite element analysis.Indian Journal of Dental Research, 21(3):425, 2010

    work page 2010

  50. [50]

    On the construction and comparison of difference schemes.SIAM journal on numerical analysis, 5(3):506–517, 1968

    Gilbert Strang. On the construction and comparison of difference schemes.SIAM journal on numerical analysis, 5(3):506–517, 1968

    work page 1968

  51. [51]

    Hamiltonian generative networks

    Peter Toth, Danilo J Rezende, Andrew Jaegle, Sébastien Racanière, Aleksandar Botev, and Irina Higgins. Hamiltonian generative networks. InInternational Conference on Learning Representations, 2019

    work page 2019

  52. [52]

    Advancing gen- eralization in pinns through latent-space representations.IEEE Trans- actions on Neural Networks and Learning Systems, 2025

    Honghui Wang, Yifan Pu, Shiji Song, and Gao Huang. Advancing gen- eralization in pinns through latent-space representations.IEEE Trans- actions on Neural Networks and Learning Systems, 2025. 36

    work page 2025

  53. [53]

    Long-time integration of parametric evolution equations with physics-informed deeponets.Journal of Com- putational Physics, 475:111855, 2023

    Sifan Wang and Paris Perdikaris. Long-time integration of parametric evolution equations with physics-informed deeponets.Journal of Com- putational Physics, 475:111855, 2023

    work page 2023

  54. [54]

    Respectingcausality is all you need for training physics-informed neural networks.arXiv preprint arXiv:2203.07404, 2022

    SifanWang, ShyamSankaran, andParisPerdikaris. Respectingcausality is all you need for training physics-informed neural networks.arXiv preprint arXiv:2203.07404, 2022

    work page arXiv 2022

  55. [55]

    Understanding and mit- igating gradient flow pathologies in physics-informed neural networks

    Sifan Wang, Yujun Teng, and Paris Perdikaris. Understanding and mit- igating gradient flow pathologies in physics-informed neural networks. SIAM Journal on Scientific Computing, 43(5):A3055–A3081, 2021

    work page 2021

  56. [56]

    Learning the solu- tion operator of parametric partial differential equations with physics- informed deeponets.Science advances, 7(40):eabi8605, 2021

    Sifan Wang, Hanwen Wang, and Paris Perdikaris. Learning the solu- tion operator of parametric partial differential equations with physics- informed deeponets.Science advances, 7(40):eabi8605, 2021

    work page 2021

  57. [57]

    When and why pinns fail to train: A neural tangent kernel perspective.Journal of Computational Physics, 449:110768, 2022

    Sifan Wang, Xinling Yu, and Paris Perdikaris. When and why pinns fail to train: A neural tangent kernel perspective.Journal of Computational Physics, 449:110768, 2022

    work page 2022

  58. [58]

    Reduced-order mod- eling for parameterized pdes via implicit neural representations.arXiv preprint arXiv:2311.16410, 2023

    Tianshu Wen, Kookjin Lee, and Youngsoo Choi. Reduced-order mod- eling for parameterized pdes via implicit neural representations.arXiv preprint arXiv:2311.16410, 2023

    work page arXiv 2023

  59. [59]

    Multiadam: Parameter-wise scale-invariant optimizer for mul- tiscale training of physics-informed neural networks

    Jiachen Yao, Chang Su, Zhongkai Hao, Songming Liu, Hang Su, and Jun Zhu. Multiadam: Parameter-wise scale-invariant optimizer for mul- tiscale training of physics-informed neural networks. InProceedings of the 40th International Conference on Machine Learning, ICML’23. JMLR.org, 2023

    work page 2023

  60. [60]

    and Gallinari, P

    Yuan Yin, Matthieu Kirchmeyer, Jean-Yves Franceschi, Alain Rako- tomamonjy, and Patrick Gallinari. Continuous pde dynamics forecasting with implicit neural representations.arXiv preprint arXiv:2209.14855, 2022

    work page arXiv 2022

  61. [61]

    The deep ritz method: a deep learning-based numerical algorithm for solving variational problems.Communications in Mathe- matics and Statistics, 6(1):1–12, 2018

    Bing Yu et al. The deep ritz method: a deep learning-based numerical algorithm for solving variational problems.Communications in Mathe- matics and Statistics, 6(1):1–12, 2018

    work page 2018

  62. [62]

    Generating videos with dynamics-aware 37 implicit generative adversarial networks

    Sihyun Yu, Jihoon Tack, Sangwoo Mo, Hyunsu Kim, Junho Kim, Jung- Woo Ha, and Jinwoo Shin. Generating videos with dynamics-aware 37 implicit generative adversarial networks. InInternational Conference on Learning Representations, 2022. 38 Appendix A. Additional Statistical Analysis on CDR Equations In this section, we provide additional statistical analysi...

    work page 2022