Advertisement

On the Trade-Off Between Number of Examples and Precision of Supervision in Regression

  • Giorgio GneccoEmail author
  • Federico Nutarelli
Conference paper
Part of the Proceedings of the International Neural Networks Society book series (INNS, volume 1)

Abstract

We investigate regression problems for which one is given the additional possibility of controlling the conditional variance of the output given the input, by varying the computational time dedicated to supervise each example. For a given upper bound on the total computational time, we optimize the trade-off between the number of examples and their precision, by formulating and solving a suitable optimization problem, based on a large-sample approximation of the output of the ordinary least squares algorithm. Considering a specific functional form for that precision, we prove that there are cases in which “many but bad” examples provide a smaller generalization error than “few but good” ones, but also that the converse can occur, depending on the “returns to scale” of the precision with respect to the computational time assigned to supervise each example. Hence, the results of this study highlight that increasing the size of the dataset is not always beneficial, if one has the possibility to collect a smaller number of more reliable examples.

Keywords

Ordinary least squares Large-sample approximation Variance control 

References

  1. 1.
    Bacigalupo, A., Gnecco, G., Lepidi, M., Gambarotta, L.: Optimal design of low-frequency band gaps in anti-tetrachiral lattice meta-materials. Compos. Part B Eng. 115, 341–359 (2017)CrossRefGoogle Scholar
  2. 2.
    Bacigalupo, A., Lepidi, M., Gnecco, G., Gambarotta, L.: Optimal design of auxetic hexachiral metamaterials with local resonators. Smart Mater. Struct. 25(5), 19 (2016). Article ID. 054009CrossRefGoogle Scholar
  3. 3.
    Hamming, R.: Numerical Methods for Scientists and Engineers, 2nd edn. McGraw-Hill, New York (1973)zbMATHGoogle Scholar
  4. 4.
    Ruud, P.A.: An Introduction to Classical Econometric Theory, 1st edn. Oxford University Press, Oxford (2000)Google Scholar
  5. 5.
    Varian, H.R.: Big data: new tricks for econometrics. J. Econ. Perspect. 28, 3–28 (2014)CrossRefGoogle Scholar
  6. 6.
    Wilkinson, J.H.: The evaluation of the zeros of ill-conditioned polynomials. Part I. Numer. Math. 1, 150–166 (1959)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.IMT School for Advanced StudiesLuccaItaly

Personalised recommendations