Hamiltonian systems are differential equations that describe systems in classical mechanics, plasma physics, and sampling problems. They exhibit many structural properties, such as a lack of attractors and the presence of conservation laws. To predict Hamiltonian dynamics based on discrete trajectory observations, the incorporation of prior knowledge about Hamiltonian structure greatly improves predictions. This is typically done by learning the system’s Hamiltonian and then integrating the Hamiltonian vector field with a symplectic integrator. For this, however, Hamiltonian data need to be approximated based on trajectory observations. Moreover, the numerical integrator introduces an additional discretization error. In this article, we show that an inverse modified Hamiltonian structure adapted to the geometric integrator can be learned directly from observations. A separate approximation step for the Hamiltonian data is avoided. The inverse modified data compensate for the discretization error such that the discretization error is eliminated. The technique is developed for Gaussian processes.

1.
E.
Hairer
,
C.
Lubich
, and
G.
Wanner
, Geometric Numerical Integration: Structure-Preserving Algorithms for Ordinary Differential Equations, Springer Series in Computational Mathematics (Springer, Berlin, 2013).
2.
M.
Betancourt
, “A conceptual introduction to Hamiltonian Monte Carlo,” arXiv:1701.02434 [stat.ME] (2018).
3.
R. I.
McLachlan
and
C.
Offen
, “
Preservation of bifurcations of Hamiltonian boundary value problems under discretisation
,”
Found. Comput. Math.
20
,
1363
1400
(
2020
).
4.
R. I.
McLachlan
and
C.
Offen
, “
Bifurcation of solutions to Hamiltonian boundary value problems
,”
Nonlinearity
31
,
2895
2927
(
2018
).
5.
C.
Offen
, “Analysis of Hamiltonian boundary value problems and symplectic integration,” doctoral thesis (Massey University, 2020).
6.
L. M.
Kreusser
,
R. I.
McLachlan
, and
C.
Offen
, “
Detection of high codimensional bifurcations in variational PDEs
,”
Nonlinearity
33
,
2335
2363
(
2020
).
7.
C.
Offen
and
S.
Ober-Blöbaum
, “Bifurcation preserving discretisations of optimal control problems,” arXiv:2107.13853 [math.OC] (2021).
8.
T.
Bertalan
,
F.
Dietrich
,
I.
Mezić
, and
I. G.
Kevrekidis
, “
On learning Hamiltonian systems from data
,”
Chaos
29
,
121107
(
2019
).
9.
A.
Zhu
,
P.
Jin
, and
Y.
Tang
, “Inverse modified differential equations for discovery of dynamics,” arXiv:2009.01058 [math.NA] (2020).
10.
S.
Ridderbusch
,
C.
Offen
,
S.
Ober-Blöbaum
, and
P.
Goulart
, “Learning ODE models with qualitative structure using Gaussian processes,” arXiv:2011.05364 [cs.LG] (2021).
11.
P.
Jin
,
Z.
Zhang
,
A.
Zhu
,
Y.
Tang
, and
G. E.
Karniadakis
, “
SympNets: Intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
,”
Neural Netw.
132
,
166
179
(
2020
).
12.
M.
David
and
F.
Méhats
, “Symplectic learning for Hamiltonian neural networks,” arXiv:2106.11753 [cs.LG] (2021).
13.
K.
Rath
,
C. G.
Albert
,
B.
Bischl
, and
U.
von Toussaint
, “
Symplectic Gaussian process regression of maps in Hamiltonian systems
,”
Chaos
31
,
053121
(
2021
).
14.
R.
Chen
and
M.
Tao
, “Data-driven prediction of general Hamiltonian dynamics via learning exactly-symplectic maps,” in Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, Proceedings of Machine Learning Research Vol. 139, edited by M. Meila and T. Zhang (PMLR, 2021), pp. 1717–1727.
15.
S.
Greydanus
,
M.
Dzamba
, and
J.
Yosinski
, “Hamiltonian neural networks,” in Advances in Neural Information Processing Systems, edited by H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché-Buc, E. Fox, and R. Garnett (Curran Associates, Inc., 2019), Vol. 32.
16.
Y. D.
Zhong
,
B.
Dey
, and
A.
Chakraborty
, “Symplectic ODE-Net: Learning Hamiltonian dynamics with control,” arXiv:1909.12077 [cs.LG] (2020).
17.
S.
Park
,
W.
Kwak
, and
H. K.
Lee
, “
Accelerated spin dynamics using deep learning corrections
,”
Sci. Rep.
10
,
13772
(
2020
).
18.
B.
Leimkuhler
and
S.
Reich
,
Simulating Hamiltonian Dynamics
(
Cambridge University Press
,
2005
).
19.
C. E.
Rasmussen
and
C. K. I.
Williams
,
Gaussian Processes for Machine Learning
(
The MIT Press
,
2005
).
20.
F.
Pedregosa
,
G.
Varoquaux
,
A.
Gramfort
,
V.
Michel
,
B.
Thirion
,
O.
Grisel
,
M.
Blondel
,
P.
Prettenhofer
,
R.
Weiss
,
V.
Dubourg
,
J.
Vanderplas
,
A.
Passos
,
D.
Cournapeau
,
M.
Brucher
,
M.
Perrot
, and
E.
Duchesnay
, “
Scikit-learn: Machine learning in Python
,”
J. Mach. Learn. Res.
12
,
2825
2830
(
2011
).
21.
C.
Offen
 (2021). “GitHub repository Christian-Offen/symplectic-shadow-integration,
Zenodo
. https://github.com/Christian-Offen/symplectic-shadow-integration.
22.
P.
Virtanen
,
R.
Gommers
,
T. E.
Oliphant
,
M.
Haberland
,
T.
Reddy
,
D.
Cournapeau
,
E.
Burovski
,
P.
Peterson
,
W.
Weckesser
,
J.
Bright
,
S. J.
van der Walt
,
M.
Brett
,
J.
Wilson
,
K. J.
Millman
,
N.
Mayorov
,
A. R. J.
Nelson
,
E.
Jones
,
R.
Kern
,
E.
Larson
,
C. J.
Carey
,
İ.
Polat
,
Y.
Feng
,
E. W.
Moore
,
J.
VanderPlas
,
D.
Laxalde
,
J.
Perktold
,
R.
Cimrman
,
I.
Henriksen
,
E. A.
Quintero
,
C. R.
Harris
,
A. M.
Archibald
,
A. H.
Ribeiro
,
F.
Pedregosa
,
P.
van Mulbregt
, and
SciPy 1.0 Contributors
, “
SciPy 1.0: Fundamental algorithms for scientific computing in Python
,”
Nat. Methods
17
,
261
272
(
2020
).
23.
E. L.
Mansfield
, “Variational problems with symmetry,” in A Practical Guide to the Invariant Calculus, Cambridge Monographs on Applied and Computational Mathematics (Cambridge University Press, 2010), pp. 206–240.
24.
R. I.
McLachlan
,
K.
Modin
, and
O.
Verdier
, “
Symplectic integrators for spin systems
,”
Phys. Rev. E
89
,
061301
(
2014
).
25.
M.
Vermeeren
, “
Modified equations for variational integrators
,”
Numer. Math.
137
,
1001
1037
(
2017
).
26.
C.
Offen
and
S.
Ober-Blöbaum
, “Symplectic integration of learned Hamiltonian systems,”
presented at Theory of Deep Learning, Isaac Newton Institute, University of Cambridge, Cambridge, UK, 9–13 August 2021 (Github, 2021), available at https://github.com/Christian-Offen/symplectic-shadow-integration/raw/master/Poster_Workshop_Cambridge.pdf.
You do not currently have access to this content.