IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v13y2022i1d10.1038_s41467-022-33126-x.html
   My bibliography  Save this article

Three learning stages and accuracy–efficiency tradeoff of restricted Boltzmann machines

Author

Listed:
  • Lennart Dabelow

    (RIKEN Center for Emergent Matter Science (CEMS))

  • Masahito Ueda

    (RIKEN Center for Emergent Matter Science (CEMS)
    The University of Tokyo)

Abstract

Restricted Boltzmann Machines (RBMs) offer a versatile architecture for unsupervised machine learning that can in principle approximate any target probability distribution with arbitrary accuracy. However, the RBM model is usually not directly accessible due to its computational complexity, and Markov-chain sampling is invoked to analyze the learned probability distribution. For training and eventual applications, it is thus desirable to have a sampler that is both accurate and efficient. We highlight that these two goals generally compete with each other and cannot be achieved simultaneously. More specifically, we identify and quantitatively characterize three regimes of RBM learning: independent learning, where the accuracy improves without losing efficiency; correlation learning, where higher accuracy entails lower efficiency; and degradation, where both accuracy and efficiency no longer improve or even deteriorate. These findings are based on numerical experiments and heuristic arguments.

Suggested Citation

  • Lennart Dabelow & Masahito Ueda, 2022. "Three learning stages and accuracy–efficiency tradeoff of restricted Boltzmann machines," Nature Communications, Nature, vol. 13(1), pages 1-11, December.
    • Handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-33126-x
    DOI: 10.1038/s41467-022-33126-x
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-022-33126-x
    File Function: Abstract
    Download Restriction: no
    File URL: https://libkey.io/10.1038/s41467-022-33126-x?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Rongxin Xia & Sabre Kais, 2018. "Quantum machine learning for electronic structure calculations," Nature Communications, Nature, vol. 9(1), pages 1-6, December.
    2. Xun Gao & Lu-Ming Duan, 2017. "Efficient representation of quantum many-body states with deep neural networks," Nature Communications, Nature, vol. 8(1), pages 1-6, December.
    3. Kenny Choo & Antonio Mezzacapo & Giuseppe Carleo, 2020. "Fermionic neural-network states for ab-initio electronic structure," Nature Communications, Nature, vol. 11(1), pages 1-7, December.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Nihal Sanjay Singh & Keito Kobayashi & Qixuan Cao & Kemal Selcuk & Tianrui Hu & Shaila Niazi & Navid Anjum Aadit & Shun Kanai & Hideo Ohno & Shunsuke Fukami & Kerem Y. Camsari, 2024. "CMOS plus stochastic nanomagnets enabling heterogeneous computers for probabilistic inference and learning," Nature Communications, Nature, vol. 15(1), pages 1-9, December.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Laura Lewis & Hsin-Yuan Huang & Viet T. Tran & Sebastian Lehner & Richard Kueng & John Preskill, 2024. "Improved machine learning algorithm for predicting ground state properties," Nature Communications, Nature, vol. 15(1), pages 1-8, December.
    2. Steve J. Bickley & Ho Fai Chan & Sascha L. Schmidt & Benno Torgler, 2020. "Quantum-Sapiens: The Quantum Bases for Human Expertise, Knowledge, and Problem-Solving," CREMA Working Paper Series 2020-18, Center for Research in Economics, Management and the Arts (CREMA).
    3. Jiequn Han & Ruimeng Hu, 2019. "Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games," Papers 1912.01809, arXiv.org, revised Jun 2020.
    4. Xiang Li & Zhe Li & Ji Chen, 2022. "Ab initio calculation of real solids via neural network ansatz," Nature Communications, Nature, vol. 13(1), pages 1-9, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-33126-x. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.