Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.06599 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909799331921920 |
|---|---|
| author | Bulusu, Sri Satish Krishna Chaitanya Sillanpää, Mikko |
| author_facet | Bulusu, Sri Satish Krishna Chaitanya Sillanpää, Mikko |
| contents | Dynamic nonlinear systems exhibit distortions arising from coupled static and dynamic effects. Their intertwined nature poses major challenges for data-driven modeling. This paper presents a theoretical framework grounded in structured decomposition, variance analysis, and task-centric complexity bounds.
The framework employs a directional lower bound on interactions between measurable system components, extending orthogonality in inner product spaces to structurally asymmetric settings. This bound supports variance inequalities for decomposed systems. Key behavioral indicators are introduced along with a memory finiteness index. A rigorous power-based condition establishes a measurable link between finite memory in realizable systems and the First Law of Thermodynamics. This offers a more foundational perspective than classical bounds based on the Second Law.
Building on this foundation, we formulate a `Behavioral Uncertainty Principle,' demonstrating that static and dynamic distortions cannot be minimized simultaneously. We identify that real-world systems seem to resist complete deterministic decomposition due to entangled static and dynamic effects. We also present two general-purpose theorems linking function variance to mean-squared Lipschitz continuity and learning complexity. This yields a model-agnostic, task-aware complexity metric, showing that lower-variance components are inherently easier to learn.
These insights explain the empirical benefits of structured residual learning, including improved generalization, reduced parameter count, and lower training cost, as previously observed in power amplifier linearization experiments. The framework is broadly applicable and offers a scalable, theoretically grounded approach to modeling complex dynamic nonlinear systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06599 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Information-Theoretic Bounds and Task-Centric Learning Complexity for Real-World Dynamic Nonlinear Systems Bulusu, Sri Satish Krishna Chaitanya Sillanpää, Mikko Machine Learning Computational Complexity Systems and Control Signal Processing Statistics Theory Dynamic nonlinear systems exhibit distortions arising from coupled static and dynamic effects. Their intertwined nature poses major challenges for data-driven modeling. This paper presents a theoretical framework grounded in structured decomposition, variance analysis, and task-centric complexity bounds. The framework employs a directional lower bound on interactions between measurable system components, extending orthogonality in inner product spaces to structurally asymmetric settings. This bound supports variance inequalities for decomposed systems. Key behavioral indicators are introduced along with a memory finiteness index. A rigorous power-based condition establishes a measurable link between finite memory in realizable systems and the First Law of Thermodynamics. This offers a more foundational perspective than classical bounds based on the Second Law. Building on this foundation, we formulate a `Behavioral Uncertainty Principle,' demonstrating that static and dynamic distortions cannot be minimized simultaneously. We identify that real-world systems seem to resist complete deterministic decomposition due to entangled static and dynamic effects. We also present two general-purpose theorems linking function variance to mean-squared Lipschitz continuity and learning complexity. This yields a model-agnostic, task-aware complexity metric, showing that lower-variance components are inherently easier to learn. These insights explain the empirical benefits of structured residual learning, including improved generalization, reduced parameter count, and lower training cost, as previously observed in power amplifier linearization experiments. The framework is broadly applicable and offers a scalable, theoretically grounded approach to modeling complex dynamic nonlinear systems. |
| title | Information-Theoretic Bounds and Task-Centric Learning Complexity for Real-World Dynamic Nonlinear Systems |
| topic | Machine Learning Computational Complexity Systems and Control Signal Processing Statistics Theory |
| url | https://arxiv.org/abs/2509.06599 |