Abstract
A new method for entropy-randomized machine learning is proposed based on empirical risk minimization instead of the exact fulfillment of empirical balance conditions. The corresponding machine learning algorithm is shown to generate a family of exponential distributions, and their structure is found.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
P. Campbell, Nature 455 (7209), 1 (2008).
Yu. S. Popkov, A. Yu. Popkov, and Yu. A. Dubnov, “Randomized machine learning,” Proceedings of the 8th International IEEE Conference on Intelligent Systems, Sofia, Bulgaria, 2016 (2016).
V. V. Voevodin and Yu. A. Kuznetsov, Matrices and Computations (Nauka, Moscow, 1984) [in Russian].
V. M. Tikhomirov, V. N. Alekseev, and S. V. Fomin, Optimal Control (Nauka, Moscow, 1979) [in Russian].
A. D. Ioffe and V. M. Tikhomirov, Theory of Extremal Problems (Nauka, Moscow, 1974; Elsevier, Amsterdam, 1978).
Ya. Z. Tsypkin, Foundations of the Theory of Learning Systems (Nauka, Moscow, 1970) [in Russian].
C. M. Bishop, Pattern Recognition and Machine Learning (Springer, Berlin, 2006).
M. A. Kaashoek, S. Seatzu, and C. van der Mee, Recent Advances in Operator Theory and Its Applications (Springer, New York, 2006).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © Yu.S. Popkov, 2018, published in Doklady Akademii Nauk, 2018, Vol. 483, No. 6.
Rights and permissions
About this article
Cite this article
Popkov, Y.S. Soft Randomized Machine Learning. Dokl. Math. 98, 646–647 (2018). https://doi.org/10.1134/S1064562418070293
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064562418070293