Using a one-dimensional model, we explore the ability of machine learning to approximate the non-interacting kinetic energy density functional of diatomics. This nonlinear interpolation between Kohn-Sham reference calculations can (i) accurately dissociate a diatomic, (ii) be systematically improved with increased reference data and (iii) generate accurate self-consistent densities via a projection method that avoids directions with no data. With relatively few densities, the error due to the interpolation is smaller than typical errors in standard exchange-correlation functionals.
REFERENCES
1.
P.
Hohenberg
and W.
Kohn
, “Inhomogeneous electron gas
,” Phys. Rev.
136
, B864
–B871
(1964
).2.
W.
Kohn
and L. J.
Sham
, “Self-consistent equations including exchange and correlation effects
,” Phys. Rev.
140
, A1133
–A1138
(1965
).3.
K.
Burke
, “Perspective on density functional theory
,” J. Chem. Phys.
136
, 150901
(2012
).4.
K.
Burke
and L. O.
Wagner
, “Dft in a nutshell
,” Int. J. Quantum Chem.
113
, 96
–101
(2013
).5.
R. M.
Dreizler
and E. K. U.
Gross
, Density Functional Theory: An Approach to the Quantum Many-Body Problem
(Springer
, 1990
).6.
Y. A.
Wang
and E. A.
Carter
, “Orbital-free kinetic-energy density functional theory
,” in Theoretical Methods in Condensed Phase Chemistry
, edited by S. D.
Schwartz
(Kluwer
, New York
, 2000
).7.
V. V.
Karasiev
, D.
Chakraborty
, and S. B.
Trickey
, “Progress on new approaches to old ideas: Orbital-free density functionals
,” in Many-Electron Approaches in Physics, Chemistry, and Mathematics
, edited by L.
Delle Site
and V.
Bach
(Springer Verlag, Kluwer
, NY
) (to be published).8.
V.
Karasiev
and S. B.
Trickey
, “Issues and challenges in orbital-free density functional calculations
,” Comput. Phys. Commun.
183
, 2519
–2527
(2012
).9.
V. V.
Karasiev
, R. S.
Jones
, S. B.
Trickey
, and F. E.
Harris
, “Properties of constraint-based single-point approximate kinetic energy functionals
,” Phys. Rev. B
80
, 245120
(2009
).10.
V. V.
Karasiev
, R. S.
Jones
, S. B.
Trickey
, and F. E.
Harris
, “Erratum: Properties of constraint-based single-point approximate kinetic energy functionals [Phys. Rev. B 80, 245120 (2009)]
,” Phys. Rev. B
87
, 239903
(2013
).11.
C. J.
Umrigar
and X.
Gonze
, “Accurate exchange-correlation potentials and total-energy components for the helium isoelectronic series
,” Phys. Rev. A
50
, 3827
–3837
(1994
).12.
M.-C.
Kim
, E.
Sim
, and K.
Burke
, “Understanding and reducing errors in density functional calculations
,” Phys. Rev. Lett.
111
, 073003
(2013
).13.
C. F. V.
Weizsäcker
, “Zur theorie der kernmassen
,” Z Phys.
96
, 431
–458
(1935
).14.
F.
Tran
and T. A.
Wesolowski
, “Link between the kinetic- and exchange-energy functionals in the generalized gradient approximation
,” Int. J. Quantum Chem.
89
, 441
–446
(2002
).15.
E.
Chacón
, J. E.
Alvarellos
, and P.
Tarazona
, “Nonlocal kinetic energy functional for nonhomogeneous electron systems
,” Phys. Rev. B
32
, 7868
–7877
(1985
).16.
P.
García-González
, J. E.
Alvarellos
, and E.
Chacón
, “Nonlocal kinetic-energy-density functionals
,” Phys. Rev. B
53
, 9509
–9512
(1996
).17.
P.
García-González
, J. E.
Alvarellos
, and E.
Chacón
, “Nonlocal symmetrized kinetic-energy density functional: Application to simple surfaces
,” Phys. Rev. B
57
, 4857
–4862
(1998
).18.
L.-W.
Wang
and M. P.
Teter
, “Kinetic-energy functional of the electron density
,” Phys. Rev. B
45
, 13196
–13220
(1992
).19.
Y. A.
Wang
, N.
Govind
, and E. A.
Carter
, “Orbital-free kinetic-energy density functionals with a density-dependent kernel
,” Phys. Rev. B
60
, 16350
–16358
(1999
).20.
J.
Xia
, C.
Huang
, I.
Shin
, and E. A.
Carter
, “Can orbital-free density functional theory simulate molecules
?” J. Chem. Phys.
136
, 084102
(2012
).21.
Y.
Ke
, F.
Libisch
, J.
Xia
, L.-W.
Wang
, and E. A.
Carter
, “Angular-momentum-dependent orbital-free density functional theory
,” Phys. Rev. Lett.
111
, 066402
(2013
).22.
C.
Huang
and E. A.
Carter
, “Nonlocal orbital-free kinetic energy density functional for semiconductors
,” Phys. Rev. B
81
, 045206
(2010
).23.
A. J.
Cohen
, P.
Mori-Sánchez
, and W.
Yang
, “Insights into current limitations of density functional theory
,” Science
321
, 792
–794
(2008
).24.
K.-R.
Müller
, S.
Mika
, G.
Rätsch
, K.
Tsuda
, and B.
Schölkopf
, “An introduction to kernel-based learning algorithms
,” IEEE Trans. Neural Network
12
, 181
–201
(2001
).25.
O.
Ivanciuc
, “Applications of support vector machines in chemistry
,” in Reviews in Computational Chemistry
, edited by Kenny
Lipkowitz
and Tom
Cundari
(Wiley
, Hoboken
, 2007
), Vol. 23
, Chap. 6, pp. 291
–400
.26.
A. P.
Bartók
, M. C.
Payne
, R.
Kondor
, and G.
Csányi
, “Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons
,” Phys. Rev. Lett.
104
, 136403
(2010
).27.
M.
Rupp
, A.
Tkatchenko
, K.-R.
Müller
, and O. A.
von Lilienfeld
, “Fast and accurate modeling of molecular atomization energies with machine learning
,” Phys. Rev. Lett.
108
, 058301
(2012
).28.
M.
Rupp
, M. R.
Bauer
, R.
Wilcken
, A.
Lange
, M.
Reutlinger
, F. M.
Boeckler
, and G.
Schneider
, “Machine learning estimates of natural product conformational energies
,” PLOS Comput. Biol.
(in press).29.
Z. D.
Pozun
, K.
Hansen
, D.
Sheppard
, M.
Rupp
, K.-R.
Müller
, and G.
Henkelman
, “Optimizing transition states via kernel-based machine learning
,” J. Chem. Phys.
136
, 174101
(2012
).30.
G.
Montavon
, M.
Rupp
, V.
Gobre
, A.
Vazquez-Mayagoitia
, K.
Hansen
, A.
Tkatchenko
, K.-R.
Müller
, and O. A.
von Lilienfeld
, “Machine learning of molecular electronic properties in chemical compound space
,” New J. Phys.
15
, 095003
(2013
).31.
J. C.
Snyder
, M.
Rupp
, K.
Hansen
, K.-R.
Müller
, and K.
Burke
, “Finding density functionals with machine learning
,” Phys. Rev. Lett.
108
, 253002
(2012
).32.
Y.
Zhao
and D.
Truhlar
, “The M06 suite of density functionals for main group thermochemistry, thermochemical kinetics, noncovalent interactions, excited states, and transition elements: Two new functionals and systematic testing of four M06-class functionals and 12 other functionals
,” Theor. Chem. Acc.
120
, 215
–241
(2008
).33.
V.
Petzold
, T.
Bligaard
, and K. W.
Jacobsen
, “Construction of new electronic density functionals with error estimation through fitting
,” Top. Catal.
55
, 402
–417
(2012
).34.
P.
Mori-Sanchez
, A. J.
Cohen
, and W.
Yang
, “Discontinuous nature of the exchange-correlation functional in strongly correlated systems
,” Phys. Rev. Lett.
102
, 066403
(2009
).35.
L. O.
Wagner
, E. M.
Stoudenmire
, K.
Burke
, and S. R.
White
, “Reference electronic structure calculations in one dimension
,” Phys. Chem. Chem. Phys.
14
, 8581
–8590
(2012
).36.
N.
Helbig
, J. I.
Fuks
, M.
Casula
, M. J.
Verstraete
, M. A. L.
Marques
, I. V.
Tokatly
, and A.
Rubio
, “Density functional theory beyond the linear regime: Validating an adiabatic local density approximation
,” Phys. Rev. A
83
, 032503
(2011
).37.
J. C.
Light
and T.
Carrington
, “Discrete-variable representations and their utilization
,” in Advances in Chemical Physics
(John Wiley & Sons, Inc.
, 2007
), pp. 263
–310
.38.
R. A.
Adams
and J. J. F.
Fournier
, Sobolev Spaces
, Pure and Applied Mathematics
(Elsevier Science
, 2003
).39.
In real calculations all densities are represented by a finite basis, and thus will have a finite L2 norm.
40.
T.
Hastie
, R.
Tibshirani
, and J.
Friedman
, The Elements of Statistical Learning. Data Mining, Inference, and Prediction
, 2nd ed. (Springer
, New York
, 2009
).41.
K.
Hansen
, G.
Montavon
, F.
Biegler
, S.
Fazli
, M.
Rupp
, M.
Scheffler
, O. A.
von Lilienfeld
, A.
Tkatchenko
, and K.-R.
Müller
, “Assessment and validation of machine learning methods for predicting molecular atomization energies
,” J. Chem. Theory Comput.
9
, 3404
–3419
(2013
).42.
G.
Montavon
, M.
Braun
, T.
Krueger
, and K.-R.
Müller
, “Analyzing local structure in kernel-based learning: Explanation, complexity, and reliability assessment
,” IEEE Signal Process. Mag.
30
, 62
–74
(2013
).43.
In situations where this is not the case (e.g., incomplete sampling of
$\protect \mathcal {M}_N$
), the predictive variance could be used to detect when leaving the interpolation domain and further reference calculations could then be done to augment the training set accordingly.44.
B.
Schölkopf
, A.
Smola
, and K. R.
Müller
, “Nonlinear component analysis as a kernel eigenvalue problem
,” Neural Comput.
10
, 1299
–1319
(1998
).45.
J. C.
Snyder
, M.
Rupp
, K.
Hansen
, K.-R.
Müller
, and K.
Burke
, “Accurate densities from inaccurate functional derivatives
” (unpublished).46.
P.
Elliott
, K.
Burke
, M. H.
Cohen
, and A.
Wasserman
, “Partition density-functional theory
,” Phys. Rev. A
82
, 024501
(2010
).47.
J. C.
Snyder
, S.
Mika
, K.
Burke
, and K.-R.
Müller
, “Kernels, pre-images and optimization
,” in Empirical Inference – Festschrift in Honor of Vladimir N. Vapnik
, edited by Bernhard
Schoelkopf
, Zhiyuan
Luo
, and Vladimir
Vovk
(Springer
, Heidelberg
) (to be published).© 2013 AIP Publishing LLC.
2013
AIP Publishing LLC
You do not currently have access to this content.