English

$\mathcal{C}^k$-continuous Spline Approximation with TensorFlow Gradient Descent Optimizers

Machine Learning 2023-03-23 v1

Abstract

In this work we present an "out-of-the-box" application of Machine Learning (ML) optimizers for an industrial optimization problem. We introduce a piecewise polynomial model (spline) for fitting of Ck\mathcal{C}^k-continuos functions, which can be deployed in a cam approximation setting. We then use the gradient descent optimization context provided by the machine learning framework TensorFlow to optimize the model parameters with respect to approximation quality and Ck\mathcal{C}^k-continuity and evaluate available optimizers. Our experiments show that the problem solution is feasible using TensorFlow gradient tapes and that AMSGrad and SGD show the best results among available TensorFlow optimizers. Furthermore, we introduce a novel regularization approach to improve SGD convergence. Although experiments show that remaining discontinuities after optimization are small, we can eliminate these errors using a presented algorithm which has impact only on affected derivatives in the local spline segment.

Keywords

Cite

@article{arxiv.2303.12454,
  title  = {$\mathcal{C}^k$-continuous Spline Approximation with TensorFlow Gradient Descent Optimizers},
  author = {Stefan Huber and Hannes Waclawek},
  journal= {arXiv preprint arXiv:2303.12454},
  year   = {2023}
}

Comments

This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in Computer Aided Systems Theory - EUROCAST 2022 and is available online at https://doi.org/10.1007/978-3-031-25312-6_68

R2 v1 2026-06-28T09:28:00.050Z