Document Type
Article
Abstract
Learning tasks involving function approximation are preva- lent in numerous domains of science and engineering. The underlying idea is to design a learning algorithm that gener- ates a sequence of functions converging to the desired target function with arbitrary accuracy by using the available data samples. In this paper, we present a novel interpretation of iterative function learning through the lens of ensemble dy- namical systems, with an emphasis on establishing the equiv- alence between convergence of function learning algorithms and asymptotic behavior of ensemble systems. In particular, given a set of observation data in a function learning task, we prove that the procedure of generating an approximation sequence can be represented as a steering problem of a dy- namic ensemble system defined on a function space. This in turn gives rise to an ensemble systems-theoretic approach to the design of “continuous-time” function learning algorithms, which have a great potential to reach better generalizability compared with classical “discrete-time” learning algorithms.
Publication Info
Preprint version When Machine Learning meets Dynamical Systems: Theory and Applications (MLmDS), AAAI 2023, 2023.
Copyright © 2023, Association for the Advancement of Artificial Intelligence (www.aaai.org), AAAI 2023 Workshop “When Machine Learning meets Dynamical Systems: Theory and Applications” (MLmDS 2023). All rights reserved.
APA Citation
Zhang, W., Narayanan, V., & Li, J. (2023). Dynamic function learning through control of ensemble systems [Preprint]. When Machine Learning meets Dynamical Systems: Theory and Applications (MLmDS), AAAI 2023, Washington, DC.
Included in
Artificial Intelligence and Robotics Commons, Dynamic Systems Commons, Numerical Analysis and Computation Commons, Numerical Analysis and Scientific Computing Commons, Theory and Algorithms Commons