REVIEW 10 cited by
Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately
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
Signed reviews
read the original abstract
Understanding natural symmetries is key to making sense of our complex and ever-changing world. Recent work has shown that neural networks can learn such symmetries directly from data using Hamiltonian Neural Networks (HNNs). But HNNs struggle when trained on datasets where energy is not conserved. In this paper, we ask whether it is possible to identify and decompose conservative and dissipative dynamics simultaneously. We propose Dissipative Hamiltonian Neural Networks (D-HNNs), which parameterize both a Hamiltonian and a Rayleigh dissipation function. Taken together, they represent an implicit Helmholtz decomposition which can separate dissipative effects such as friction from symmetries such as conservation of energy. We train our model to decompose a damped mass-spring system into its friction and inertial terms and then show that this decomposition can be used to predict dynamics for unseen friction coefficients. Then we apply our model to real world data including a large, noisy ocean current dataset where decomposing the velocity field yields useful scientific insights.
Forward citations
Cited by 10 Pith papers
-
CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts
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.
-
Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach
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.
-
History-informed Lagrangian Neural Networks
HiLNN conditions Lagrangian dynamics on a latent context encoded from position history, enabling position-only long-horizon forecasting that outperforms LNN/HNN/Neural ODE baselines on three pendulum settings.
-
CoSynFlow: Conformal Symplectic Neural Flows for Cross-System Prediction of Dissipative Hamiltonian Dynamics
CoSynFlow composes symplectic shear flows with explicit conformal scaling so that the learned map satisfies the exact conformal symplectic relation, enabling cross-system prediction for dissipative Hamiltonian dynamics.
-
Geometric Contact Flows: Contactomorphisms for Dynamics and Control
Geometric Contact Flows learn dissipative dynamical systems by mapping a simple contact-Hamiltonian baseline through learned contact-preserving transformations, with ensemble uncertainty and geodesic reshaping for rob...
-
Hamiltonian-based neural networks for systems under nonholonomic constraints
A Hamiltonian neural network with three parallel networks can recover the Hamiltonian, constraint matrix, and Lagrange multipliers of nonholonomically constrained systems from clean or noisy phase-space data.
-
Learning Generalized Hamiltonian Dynamics with Stability from Noisy Trajectory Data
The paper extends symplectic spectral Gaussian processes with energy, volume, and Lyapunov regularizers to learn conservative, dissipative, and port-Hamiltonian dynamics from noisy data.
-
SlotPi: Physics-informed Object-centric Reasoning Models
SlotPi combines a learned Hamiltonian energy module with spatiotemporal attention to improve object-centric video prediction and visual question answering on several datasets.
-
Learning mechanical systems from real-world data using discrete forced Lagrangian dynamics
A discrete forced Lagrangian neural network learns conservative and dissipative dynamics from position data alone and produces structure-preserving rollouts.
-
Control-Oriented System Identification: Classical, Learning, and Physics-Informed Approaches
A survey and tutorial that classifies control-oriented, physics-informed system identification into direct parameterization, hard-constraint, and soft-constraint approaches and illustrates them with reproducible examples.
Discussion (0). Continue with ORCID to comment.