Pith. sign in

REVIEW 54 cited by

Lagrangian Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.04630 v2 pith:QIPAWCYD submitted 2020-03-10 cs.LG math.DSphysics.comp-phphysics.data-anstat.ML

Lagrangian Neural Networks

classification cs.LG math.DSphysics.comp-phphysics.data-anstat.ML
keywords modelsneuralapproachcanonicallagrangiannetworkssymmetriesconservation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Accurate models of the world are built upon notions of its underlying symmetries. In physics, these symmetries correspond to conservation laws, such as for energy and momentum. Yet even though neural network models see increasing use in the physical sciences, they struggle to learn these symmetries. In this paper, we propose Lagrangian Neural Networks (LNNs), which can parameterize arbitrary Lagrangians using neural networks. In contrast to models that learn Hamiltonians, LNNs do not require canonical coordinates, and thus perform well in situations where canonical momenta are unknown or difficult to compute. Unlike previous approaches, our method does not restrict the functional form of learned energies and will produce energy-conserving models for a variety of tasks. We test our approach on a double pendulum and a relativistic particle, demonstrating energy conservation where a baseline approach incurs dissipation and modeling relativity without canonical coordinates where a Hamiltonian approach fails. Finally, we show how this model can be applied to graphs and continuous systems using a Lagrangian Graph Network, and demonstrate it on the 1D wave equation.

discussion (0)

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

Forward citations

Cited by 54 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators

    cs.LG 2026-06 unverdicted novelty 8.0

    GENERIC-FNO is the first neural operator to embed the complete GENERIC (metriplectic) structure directly in function space, enforcing energy conservation and entropy production exactly by construction across multiple ...

  2. GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators

    cs.LG 2026-06 accept novelty 7.5

    GENERIC-FNO embeds full metriplectic GENERIC structure in function space via projection-sandwiched Fourier multipliers, enforcing exact degeneracy and thermodynamic laws by construction.

  3. The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning

    cs.LG 2026-07 accept novelty 7.0

    In a port-Hamiltonian DEQ with learned initialization, the equilibrium equals the start to numerical precision and contributes +0.00 pp accuracy in 18 of 19 runs; a four-test diagnostic exposes the no-op.

  4. CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts

    cs.RO 2026-07 conditional novelty 7.0

    Exact symplectic learning extends to open robotic systems via an algebraic structured canonical lift, improving OOD autoregressive prediction on pendulum, quadrotor, and quadruped with parameter-efficient SympNets.

  5. Embedding Hybrid Systems into Continuous Latent Vector Fields

    cs.LG 2026-06 unverdicted novelty 7.0

    An n-dimensional hybrid system embeds into a continuous vector field in m > 2n dimensions, enabling latent Neural ODEs with consistency losses to recover hybrid flows from time series.

  6. Between Amnesia and Chaos: A Memory Stability Expressivity Trilemma for Trainable Dissipative Oscillator Networks

    cs.LG 2026-06 unverdicted novelty 7.0

    Trainable dissipative oscillator networks exhibit a trilemma in which damping governs memory horizon, gradient stability, and Lyapunov exponent, with learned substrates outperforming frozen ones only at short horizons...

  7. Learning Transferable Predictability Representations

    cs.LG 2026-05 unverdicted novelty 7.0

    GON uses 2-jet features and an anchor-and-variance objective to fix gauge freedom in ordinal predictability scoring, enabling pretrained initialization to outperform scratch training on held-out dynamical systems.

  8. Attention-based optimizer for symmetry finding

    quant-ph 2026-05 unverdicted novelty 7.0

    A Set-Transformer architecture with self-attention encodes Pauli-string correlations, optimizes via commutation objective, and finds symmetries with near-deterministic success on physical models like Ising and Toric code.

  9. Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    FISolver trains a compact LLM on backward-generated (differential equation, first integral) pairs and uses guided reinforcement learning to outperform larger models and Mathematica on first-integral benchmarks at lower cost.

  10. Hamiltonian-Inspired Attention Mechanism for Scalable RF Transmitter Fingerprinting

    eess.SP 2026-05 unverdicted novelty 7.0

    Hamiltonian Transformer with norm-preserving attention and phase embeddings outperforms baselines in RF fingerprinting on WiSig dataset, reaching 99.12% same-day accuracy and 61.64% at 150 transmitters.

  11. Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery

    cs.RO 2026-05 unverdicted novelty 7.0

    VHYDRO is a support-safe variational hybrid filter that jointly recovers continuous latent states, discrete contact modes, and sparse port-Hamiltonian laws per regime while preventing loss of feasible transitions.

  12. Detecting Deepfakes via Hamiltonian Dynamics

    cs.CV 2026-05 unverdicted novelty 7.0

    HAAD detects deepfakes by modeling latent manifolds as potential energy surfaces and quantifying instability via Hamiltonian trajectory statistics such as action and energy dissipation.

  13. Parametric Interpolation of Dynamic Mode Decomposition for Predicting Nonlinear Systems

    eess.SY 2026-04 unverdicted novelty 7.0

    piDMD learns a single parameter-affine Koopman surrogate ROM from training samples at multiple parameters to predict dynamics at unseen parameters with improved robustness over interpolation baselines.

  14. When is a System Discoverable from Data? Discovery Requires Chaos

    math.DS 2025-11 conditional novelty 7.0

    Uniquely identifying an ODE from trajectory data depends on the trajectory filling enough of the state space: chaos on a high-dimensional attractor yields analytic discoverability, while first integrals preclude it.

  15. Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach

    cs.LG 2025-09 conditional novelty 7.0

    A reduced-order Hamiltonian neural network (RO-HNN) learns a symplectic low-dimensional embedding and the dynamics on it, enabling stable long-term prediction for high-dimensional Hamiltonian systems up to 600 DoF.

  16. Latent Lie-Poisson Neural Networks (LLPNNs): Discovering the motion of Lie-Poisson systems through observable data and latent dynamics

    cs.LG 2026-07 conditional novelty 6.5

    LLPNNs recover latent Lie–Poisson momentum dynamics from observable configuration and velocity data by exploiting conserved spatial momentum and coadjoint reconstruction.

  17. Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulations

    cs.LG 2026-07 conditional novelty 6.0

    Replacing explicit neural network stacks with self-consistent fixed-point iterations, and warm-starting the solver across timesteps, gives 2-5x cheaper molecular dynamics force evaluation at matched accuracy.

  18. Can AI Follow In Einstein's Footsteps?

    physics.hist-ph 2026-07 conditional novelty 6.0

    AI for physics has moved from explicit equation discovery to black-box prediction, a trajectory the authors argue reverses the historical progression of human physics, leaving the invention of new mathematical framewo...

  19. Quantum Port-Hamiltonian Neural Networks: Learning Conservative and Dissipative Dynamics via Measurement-Induced Nonlinearity

    cs.LG 2026-07 unverdicted novelty 6.0

    Q-pHNNs learn classical conservative and dissipative dynamics by mapping the port-Hamiltonian J matrix to unitary gates and the R matrix to mid-circuit measurement nonlinearity, enforcing structure by construction.

  20. Quantum Port-Hamiltonian Neural Networks: Learning Conservative and Dissipative Dynamics via Measurement-Induced Nonlinearity

    cs.LG 2026-07 reject novelty 6.0

    A quantum-circuit framework learns conservative and dissipative classical dynamics by encoding J as unitary gates and R as measurement-induced nonlinearity, demonstrated only on small toy systems.

  21. Symplectic Neural Networks for learning Generalized Hamiltonians

    cs.LG 2026-06 unverdicted novelty 6.0

    Symplectic neural networks enable efficient training of Hamiltonian models with implicit integrators for improved energy conservation in chaotic systems.

  22. SPADE: Structure-Prior Adaptive Decision Estimation

    cs.AI 2026-06 unverdicted novelty 6.0

    SPADE adaptively enforces or relaxes structure priors in estimators via exact specification tests and Stein-unbiased James-Stein shrinkage with claimed oracle guarantees.

  23. Locally Stable Neural ODEs with Characterized Region of Attraction

    math.OC 2026-06 unverdicted novelty 6.0

    Neural ODEs constrained by the gradient of a jointly learned maximal Lyapunov function universally approximate locally exponentially stable dynamics within a region of attraction exactly given by the Lyapunov 1-sublevel set.

  24. NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics

    cs.CV 2026-06 unverdicted novelty 6.0

    NEXUS introduces a graph-based neural energy-field model that derives forces from scalar energy and dissipation terms to achieve physically consistent contact-rich 3D dynamics.

  25. Least-Action-Guided Diffusion for Physical Extrapolation

    cs.LG 2026-06 unverdicted novelty 6.0

    LAPG combines conditional score-based diffusion with an action-derived guidance score to reduce phase drift and preserve physical invariants during temporal, parameter, and geometric extrapolation on free-fall, spring...

  26. Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems

    cs.LG 2026-06 unverdicted novelty 6.0

    MF-Net learns a shared field state and mechanical transition rule from trajectories to deliver competitive forecasting and recoverable relation matrices on Lorenz-96 and real systems.

  27. NeuROK: Generative 4D Neural Object Kinematics

    cs.CV 2026-05 unverdicted novelty 6.0

    NeuROK learns a data-driven latent kinematic parameterization on a large 4D dataset to generate realistic object deformations by simulating dynamics only in low-dimensional latent space via Lagrangian mechanics.

  28. Learning partially observed systems with neural Hamiltonian ordinary differential equations

    cs.LG 2026-05 unverdicted novelty 6.0

    NHODE framework learns partially observed dynamical systems by combining Hamiltonian neural networks with neural ODEs, enforcing energy conservation and improving long-horizon stability over data-driven baselines on m...

  29. Integrable Elasticity via Neural Demand Potentials

    cs.LG 2026-05 unverdicted novelty 6.0

    ICDN is a neural network that models log-demand from log-prices so elasticities can be derived exactly by differentiation, showing better out-of-sample performance than log-log benchmarks on beer sales data.

  30. Mechanisms of Misgeneralization in Physical Sequence Modeling

    cs.LG 2026-05 unverdicted novelty 6.0

    Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance o...

  31. LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations

    cs.LG 2026-05 unverdicted novelty 6.0

    LaWM induces latent transitions from a learned discrete variational principle rather than an unconstrained neural predictor, yielding improved physical consistency on synthetic dynamics and robot benchmarks.

  32. Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

    cs.AI 2026-05 unverdicted novelty 6.0

    Hamiltonian World Models structure latent dynamics around energy-conserving Hamiltonian evolution to produce physically grounded, action-controllable predictions for embodied decision making.

  33. Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics

    cs.LG 2026-05 unverdicted novelty 6.0

    Mesh Field Theory reduces mesh-based physics to port-Hamiltonian form with topology fixing interconnections and metrics entering only via constitutive relations, enabling MeshFT-Net to achieve near-zero energy drift, ...

  34. Dissipative Latent Residual Physics-Informed Neural Networks for Modeling and Identification of Electromechanical Systems

    cs.LG 2026-04 unverdicted novelty 6.0

    DiLaR-PINN learns dissipative effects in electromechanical systems via a skew-dissipative latent residual PINN that guarantees non-increasing energy and uses recurrent curriculum training for partial observations.

  35. Gradient Networks for Universal Magnetic Modeling of Synchronous Machines

    eess.SY 2026-02 conditional novelty 6.0

    A gradient-network model trained on sparse flux-linkage/current data reproduces the saturable, angle-periodic magnetic maps of a 5.6-kW synchronous machine while enforcing reciprocity, convexity, and smoothness by con...

  36. Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach

    cs.LG 2025-09 unverdicted novelty 6.0

    RO-HNN combines a geometrically-constrained symplectic autoencoder with a geometric Hamiltonian neural network to enable physically consistent predictions on high-dimensional systems via model-order reduction.

  37. SLIDE: A machine-learning based method for forced dynamic response estimation of multibody systems

    cs.LG 2024-09 unverdicted novelty 6.0

    SLIDE is a deep learning estimator that truncates initial effects via complex eigenvalues of linearized equations to predict output sequences of damped multibody systems, reporting speedups up to several million times.

  38. Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

    cs.LG 2021-04 accept novelty 6.0

    Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.

  39. Data-free neural PDE solvers based on Graph Neural Networks and weak forms

    cs.CE 2026-07 conditional novelty 5.0

    A graph-neural-network PDE solver trained on the weak-form force residual — no simulation data — reports residual convergence below 1% on unseen load cases and one modified geometry, with residual-based test-time refinement.

  40. CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts

    cs.RO 2026-07 conditional novelty 5.0

    Lifting non-conservative, actuated, and contact-constrained robot dynamics into an exactly symplectic phase-space map yields state-of-the-art out-of-distribution autoregressive rollout error at low parameter and FLOP cost.

  41. Geometry-Conditioned Fourier Neural Operators for Cubic Nonlinear Schrodinger Dynamics on Periodic Domains

    cs.LG 2026-06 unverdicted novelty 5.0

    A geometry-conditioned FNO is trained on pseudospectral data to approximate the one-step operator for cubic NLS on 2D tori and reproduces distinct H²-norm growth on rational versus irrational aspect ratios.

  42. Robots Need More than VLA and World Models

    cs.RO 2026-06 unverdicted novelty 5.0

    The paper identifies four missing interfaces (data autolabelling, embodiment retargeting, physics-grounded world models, and video-based reward inference) as the central bottleneck beyond VLA scaling for robot intelligence.

  43. Physically Viable World Models: A Case for Query-Conditioned Embodied AI

    cs.AI 2026-05 unverdicted novelty 5.0

    Embodied AI requires query-conditioned world models that select the simplest physical abstraction sufficient to answer intervention queries.

  44. Physics-Informed Graph Neural Network Surrogates for Turbulent Nanoparticle Dispersion in Dental Clinical Environments

    cs.LG 2026-05 unverdicted novelty 5.0

    ELGIN is a graph-based physics-informed surrogate model that predicts carrier flow and polydisperse particle motion in dental aerosol scenarios, achieving lower tracking errors and 37x speedup versus full OpenFOAM CFD...

  45. Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

    cs.AI 2026-05 unverdicted novelty 5.0

    The paper introduces Hamiltonian World Models by encoding observations into structured latent phase space and evolving states via Hamiltonian-inspired dynamics for physically meaningful rollouts in embodied AI.

  46. Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

    cs.AI 2026-05 unverdicted novelty 5.0

    Proposes Hamiltonian World Models as a physically grounded framework encoding observations into latent phase space and evolving them via Hamiltonian dynamics with control and dissipation for embodied prediction and planning.

  47. Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics

    cs.LG 2026-05 unverdicted novelty 5.0

    Mesh Field Theory proves mesh-based continuum physics reduces to port-Hamiltonian dynamics with topology fixing interconnections and metrics entering only via constitutive relations, enabling MeshFT-Net for stable, da...

  48. A hierarchy of thermodynamics learning frameworks for inelastic constitutive modeling

    cond-mat.mtrl-sci 2026-03 conditional novelty 5.0

    With identical neural building blocks, dissipation-potential, GSM, and metriplectic models all learn accurate inelastic stress responses; performance differences are modest and dataset-dependent.

  49. Optimal transport by a Lagrangian dynamics of population distribution

    cond-mat.dis-nn 2025-10 unverdicted novelty 5.0

    A quadratic Lagrangian incorporating dissipation models human mobility from population distributions and fits both synthetic and empirical data, showing comparable inertia and dissipation effects.

  50. Geometry-Conditioned Fourier Neural Operators for Cubic Nonlinear Schrodinger Dynamics on Periodic Domains

    cs.LG 2026-06 conditional novelty 4.0

    A Fourier neural operator conditioned on the torus aspect-ratio parameter learns NLS dynamics and reproduces stronger H²-norm growth on rational tori than on irrational tori.

  51. Can Predicted Dynamics Exist in the Physical World?

    cs.RO 2026-05 unverdicted novelty 4.0

    Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention...

  52. World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications

    cs.LG 2026-05 unverdicted novelty 3.0

    The paper delivers a multi-axis taxonomy for world models that maps architectures, training families, reasoning strategies, and domains from early cognitive foundations through systems such as Dreamer, MuZero, and Sor...

  53. L-Learning : A Lyapunov-Based Approach Leveraging Lagrangian Mechanics for Efficient and Stable Robot Tracking

    cs.RO 2026-05 unverdicted novelty 3.0

    L-Learning learns the system's energy function from data to deliver stable, accurate, and sample-efficient robot trajectory tracking with closed-loop stability guarantees.

  54. A comparative study of accuracy and rollout stability of temporal surrogate models

    cs.LG 2026-05 unverdicted novelty 3.0

    Comparative experiments on three chaotic systems find that architectures using integrator-like updates exhibit lower bias, reduced perturbation amplification, and more stable long-horizon rollouts than other common de...