Journal of Mathematical Chemistry

, Volume 50, Issue 7, pp 2043–2050 | Cite as

Classification of nodal pockets in many-electron wave functions via machine learning

  • Erin LeDell
  • Prabhat
  • Dmitry Yu. Zubarev
  • Brian Austin
  • William A. LesterJr.
Original Paper


Accurate treatment of electron correlation in quantum chemistry requires solving the many-electron problem. If the nodal surface of a many-electron wave function is available even in an approximate form, the fixed-node diffusion Monte Carlo (FNDMC) approach from the family of quantum Monte Carlo methods can be successfully used for this purpose. The issue of description and classification of nodal surfaces of fermionic wave functions becomes central for understanding the basic properties of many-electron wave functions and for the control of accuracy and computational efficiency of FNDMC computations. In this work, we approach the problem of automatic classification of nodal pockets of many-electron wave functions. We formulate this problem as that of binary classification and apply a number of techniques from the machine learning literature. We apply these techniques on a range of atoms of light elements and demonstrate varying degrees of success. We observe that classifiers with relatively simple geometry perform poorly on the classification task; methods based on a random collection of tree-based classifiers appear to perform best. We conclude with thoughts on computational challenges and complexity associated with applying these techniques to heavier atoms.


Binary classification Machine learning Many-body methods Quantum chemistry Fixed-node diffusion Monte Carlo Electronic structure theory 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hohenberg P., Kohn W.: Phys. Rev. B 136, B864 (1964)CrossRefGoogle Scholar
  2. 2.
    Kohn W., Sham L.J.: Phys. Rev. B 140, 1133 (1965)CrossRefGoogle Scholar
  3. 3.
    Roothaan C.C.J.: Rev. Mod. Phys. 23, 69 (1951)CrossRefGoogle Scholar
  4. 4.
    Hammond B.L., Lester W.A. Jr., Reynolds P.J.: Monte Carlo Methods in Ab Initio Quantum Chemistry: Quantum Monte Carlo for Molecules. World Scientific, Hackensack (1994)CrossRefGoogle Scholar
  5. 5.
    Austin B.M., Zubarev D.Yu., Lester W.A. Jr.: Chem. Rev. 112, 263 (2012)CrossRefGoogle Scholar
  6. 6.
    Grossman J.C.: J. Chem. Phys. 117, 1434 (2002)CrossRefGoogle Scholar
  7. 7.
    Ceperley D.M.: J. Stat. Phys. 63, 1237 (1991)CrossRefGoogle Scholar
  8. 8.
    Bajdich M., Wagner L.K., Drobny G., Mitas L., Schmidt K.E.: Phys. Rev. Lett. 96, 130201 (2006)CrossRefGoogle Scholar
  9. 9.
    Glauser W.A., Brown W.R., Lester W.A., Bressanini D., Hammond B.L., Koszykowski M.L.: J. Chem. Phys. 97, 9200 (1992)CrossRefGoogle Scholar
  10. 10.
    Bressanini D., Reynolds P.J.: Phys. Rev. Lett. 95, 110201 (2005)CrossRefGoogle Scholar
  11. 11.
    Aspuru-Guzik A., Salomon-Ferrer R., Austin B., Perusquia-Flores R., Griffin M.A., Oliva R.A., Skinner D., Domin D., Lester W.A. Jr.: J. Comput. Chem. 26, 856 (2005)CrossRefGoogle Scholar
  12. 12.
    Jastrow R.: Phys. Rev. 98, 1479 (1955)CrossRefGoogle Scholar
  13. 13.
    The R Project for Statistical Computing,
  14. 14.
  15. 15.
    Cortes C., Vapnik V.: Mach. Learn. 20, 237 (1995)Google Scholar
  16. 16.
    Breiman L., Friedman J.H., Olshen R.A., Stone C.J.: Classification and Regression Trees. Wadsworth & Brooks/Cole Advanced Books, Monterey (1984)Google Scholar
  17. 17.
    Hastie T., Tibshirani R., Friedman J.H.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, New York (2001)Google Scholar
  18. 18.
    Cover T.M., Hart P.E.: IEEE Trans. Inform. Theory 13, 21 (1967)CrossRefGoogle Scholar
  19. 19.
    Breiman L.: Mach. Learn. 45, 1 (2001)Google Scholar
  20. 20.
    Ho T.: IEEE Trans. Patt. Anal. Mach. Intell. 20, 832 (1998)CrossRefGoogle Scholar
  21. 21.
  22. 22.
    Friedman J.H.: Stochastic Gradient Boosting. Stanford University, Stanford (1999)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Erin LeDell
    • 1
  • Prabhat
    • 2
  • Dmitry Yu. Zubarev
    • 3
  • Brian Austin
    • 4
  • William A. LesterJr.
    • 3
  1. 1.Division of BiostatisticsUC BerkeleyBerkeleyUSA
  2. 2.Computational Research DivisionLawrence Berkeley National LaboratoryBerkeleyUSA
  3. 3.Department of ChemistryUC BerkeleyBerkeleyUSA
  4. 4.National Energy Research Scientific Computing CenterLawrence Berkeley National LaboratoryBerkeleyUSA

Personalised recommendations