Article
Version 1
This version is not peer-reviewed
The Finite–Time Turnpike Property in Machine Learning
Version 1
: Received: 16 August 2024 / Approved: 17 August 2024 / Online: 20 August 2024 (05:02:49 CEST)
How to cite: Gugat, M. The Finite–Time Turnpike Property in Machine Learning. Preprints 2024, 2024081283. https://doi.org/10.20944/preprints202408.1283.v1 Gugat, M. The Finite–Time Turnpike Property in Machine Learning. Preprints 2024, 2024081283. https://doi.org/10.20944/preprints202408.1283.v1
Abstract
The finite-time turnpike property describes the situation in an optimal control problem where an optimal trajectory reaches the desired state before the end of the time interval and remains there.
We consider a machine learning problem with a neural ordinary differential equation that can be seen as a homogenization of a deep ResNet.
We show that with appropriate scaling of the quadratic control cost and the non-smooth tracking term the optimal control problem has the finite-time turnpike property, that is the desired state is reached in the interior of the time interval and the optimal state remains there until the terminal time $T$.
This property is useful to achieve a compromise between the depth of the network and the size of the optimal system parameters which we hope will be useful to determine optimal depths for neural network architectures in the future.
Keywords
neural ode; turnpike property; finite-time turnpike; non-smooth loss function; tracking term
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment