Analog Macromodeling using Kernel Methods
See where this sits in the topic map →Summary AI-generated
- TL;DR
- This paper explores the potential of kernel-based regression, a general class of functional representation techniques, for solving the nonlinear model reduction problem.
- Problem
- Not specified in the abstract.
- Method
- The authors adopt a kernel-based viewpoint that provides a convenient computational framework for regression, unifying and extending existing polynomial and piecewise-linear reduction methods.
- Results
- Not specified in the abstract.
- Contributions
- Not specified in the abstract.
- Limitations
- Not specified in the abstract.
- Takeaways
- By leveraging familiar linear system manipulation techniques in a nonlinear context, kernels offer insight into building more powerful modeling strategies, including an SVD-like technique for automatic model compression that systematically identifies redundancies and controls approximation error.
- Applications
- Not specified in the abstract.
- Topics
- Analog Macromodeling; Kernel Methods
- For industry
- Not specified in the abstract.
- Why it matters
- Not specified in the abstract.
Abstract
In this paper we explore the potential of using a general class of functional representation techniques, kernel-based regression, in the nonlinear model reduction problem. The kernel-based viewpoint provides a convenient computational framework for regression, unifying and extending the previously proposed polynomial and piecewise-linear reduction methods. Furthermore, as many familiar methods for linear system manipulation can be leveraged in a nonlinear context, kernels provide insight into how new, more powerful, nonlinear modeling strategies can be constructed. We present an SVD-like technique for automatic compression of nonlinear models that allows systematic identification of model redundancies and rigorous control of approximation error.