IDEAS home Printed from https://ideas.repec.org/a/hin/jnlmpe/1463094.html
   My bibliography  Save this article

Performance of Post-Training Two-Bits Uniform and Layer-Wise Uniform Quantization for MNIST Dataset from the Perspective of Support Region Choice

Author

Listed:
  • Stefan Tomić
  • Jelena Nikolić
  • Zoran Perić
  • Danijela Aleksić
  • Hao Gao

Abstract

This paper contributes to the goal of finding an efficient compression solution for post-training quantization from the perspective of support region choice under the framework of low-bit uniform quantization. The decision to give preference to uniform quantization comes from the fact that support region choice is the most sensitive in the uniform quantization of nonuniform sources (e.g., Laplacian sources). Therefore, in this paper, we analyse in detail how the choice of the support region influences the performance of two-bits uniform quantization, measured with signal to quantization noise ratio (SQNR), and the accuracy of the compressed neural network (NN) model. We provide experimental and theoretical results for a few significant cases of two-bits uniform quantizer design, where we assume that Laplacian source models the distribution of weights in our fully connected NN. We opt for Laplacian distribution since it models well weights of NNs. Specifically, we analyse whether it is possible to apply the simplest uniform quantization in trained NN model weight representation with a bit rate of R = 2 bit/sample while preserving the accuracy of the model to a great extent. Also, our goal is to determine whether the choice of the key parameter of two-bits uniform quantizer (support region threshold) equally reflects on both, SQNR and accuracy. Moreover, we extend our analysis to the application of layer-wise two-bits uniform quantization in order to examine whether it is possible to achieve an additional improvement of the accuracy of our NN model for the MNIST dataset. We believe that the detailed analysis of post-training quantization described and conducted in this paper is very useful for all further research studies of this very current topic, especially due to the fact that the problem regarding post-training quantization is addressed from a particularly important perspective of choosing the support region.

Suggested Citation

  • Stefan Tomić & Jelena Nikolić & Zoran Perić & Danijela Aleksić & Hao Gao, 2022. "Performance of Post-Training Two-Bits Uniform and Layer-Wise Uniform Quantization for MNIST Dataset from the Perspective of Support Region Choice," Mathematical Problems in Engineering, Hindawi, vol. 2022, pages 1-15, April.
  • Handle: RePEc:hin:jnlmpe:1463094
    DOI: 10.1155/2022/1463094
    as

    Download full text from publisher

    File URL: http://downloads.hindawi.com/journals/mpe/2022/1463094.pdf
    Download Restriction: no

    File URL: http://downloads.hindawi.com/journals/mpe/2022/1463094.xml
    Download Restriction: no

    File URL: https://libkey.io/10.1155/2022/1463094?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
    ---><---

    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:hin:jnlmpe:1463094. 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.

    We have no bibliographic references for this item. You can help adding them by using 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: Mohamed Abdelhakeem (email available below). General contact details of provider: https://www.hindawi.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.