IDEAS home Printed from https://ideas.repec.org/p/osf/osfxxx/wa98j.html
   My bibliography  Save this paper

A New Lower Bound for Kullback-Leibler Divergence Based on Hammersley-Chapman-Robbins Bound

Author

Listed:
  • Nishiyama, Tomohiro

Abstract

In this paper, we derive a useful lower bound for the Kullback-Leibler divergence (KL-divergence) based on the Hammersley-Chapman-Robbins bound (HCRB). The HCRB states that the variance of an estimator is bounded from below by the Chi-square divergence and the expectation value of the estimator. By using the relation between the KL-divergence and the Chi-square divergence, we show that the lower bound for the KL-divergence which only depends on the expectation value and the variance of a function we choose. This lower bound can also be derived from an information geometric approach. Furthermore, we show that the equality holds for the Bernoulli distributions and show that the inequality converges to the Cram\'{e}r-Rao bound when two distributions are very close. We also describe application examples and examples of numerical calculation.

Suggested Citation

  • Nishiyama, Tomohiro, 2019. "A New Lower Bound for Kullback-Leibler Divergence Based on Hammersley-Chapman-Robbins Bound," OSF Preprints wa98j, Center for Open Science.
    • Handle: RePEc:osf:osfxxx:wa98j
    DOI: 10.31219/osf.io/wa98j
    as

    Download full text from publisher

    File URL: https://osf.io/download/5d1693358a17d50018051984/
    Download Restriction: no
    File URL: https://libkey.io/10.31219/osf.io/wa98j?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. Masashi Sugiyama & Taiji Suzuki & Shinichi Nakajima & Hisashi Kashima & Paul Bünau & Motoaki Kawanabe, 2008. "Direct importance estimation for covariate shift adaptation," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 60(4), pages 699-746, 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. Nishiyama, Tomohiro, 2019. "Monotonically Decreasing Sequence of Divergences," OSF Preprints wr2s6, Center for Open Science.

    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. Yannis Yatracos, 2013. "Equal percent bias reduction and variance proportionate modifying properties with mean–covariance preserving matching," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 65(1), pages 69-87, February.
    2. Byol Kim & Song Liu & Mladen Kolar, 2021. "Two‐sample inference for high‐dimensional Markov networks," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 83(5), pages 939-962, November.
    3. Masahiro Kato & Hikaru Kawarazaki, 2019. "Model Specification Test with Unlabeled Data: Approach from Covariate Shift," Papers 1911.00688, arXiv.org, revised Feb 2020.
    4. Zhexiao Lin & Peng Ding & Fang Han, 2023. "Estimation Based on Nearest Neighbor Matching: From Density Ratio to Average Treatment Effect," Econometrica, Econometric Society, vol. 91(6), pages 2187-2217, November.
    5. Dylan Brewer & Alyssa Carlson, 2024. "Addressing sample selection bias for machine learning methods," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 39(3), pages 383-400, April.
    6. Yukitoshi Matsushita & Taisuke Otsu & Keisuke Takahata, 2022. "Estimating density ratio of marginals to joint: Applications to causal inference," STICERD - Econometrics Paper Series 619, Suntory and Toyota International Centres for Economics and Related Disciplines, LSE.
    7. Sheng, Haiyang & Yu, Guan, 2023. "TNN: A transfer learning classifier based on weighted nearest neighbors," Journal of Multivariate Analysis, Elsevier, vol. 193(C).
    8. Abdolnasser Sadeghkhani & Yingwei Peng & Chunfang Devon Lin, 2019. "A Parametric Bayesian Approach in Density Ratio Estimation," Stats, MDPI, vol. 2(2), pages 1-13, March.
    9. Jiaming Mao & Jingzhi Xu, 2020. "Ensemble Learning with Statistical and Structural Models," Papers 2006.05308, arXiv.org.
    10. Jiaming Mao & Zhesheng Zheng, 2020. "Structural Regularization," Papers 2004.12601, arXiv.org, revised Jun 2020.
    11. Masahiro Kato & Masatoshi Uehara & Shota Yasui, 2020. "Off-Policy Evaluation and Learning for External Validity under a Covariate Shift," Papers 2002.11642, arXiv.org, revised Oct 2020.
    12. Sookyo Jeong & Hongseok Namkoong, 2020. "Assessing External Validity Over Worst-case Subpopulations," Papers 2007.02411, arXiv.org, revised Feb 2022.
    13. Masashi Sugiyama & Taiji Suzuki & Takafumi Kanamori, 2012. "Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 64(5), pages 1009-1044, October.
    14. Hofer, Vera, 2015. "Adapting a classification rule to local and global shift when only unlabelled data are available," European Journal of Operational Research, Elsevier, vol. 243(1), pages 177-189.

    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:osf:osfxxx:wa98j. 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: OSF (email available below). General contact details of provider: https://osf.io/preprints/ .

    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.