OpenAlex ·
Generalization as a robust performance property of learning-enabled dynamical systems
- Published
- Source
- OpenAlex
- DOI
- 10.48550/arxiv.2608.30431
- Original
- Read it at the publisher
- Topics
Abstract
By focusing on algorithmic stability as a means of establishing out-of-sample bounds, we provide a system-theoretic interpretation of generalization in learning-enabled dynamical systems arising in data-driven optimization and feedback control approximation. Given two neighboring datasets, we specifically model sample replacement as an exogenous disturbance acting on a sensitivity system, while the incremental behavior of the data-dependent operator is encoded through an integral quadratic constraint. By relying on dissipativity arguments, we establish a matrix inequality-based certificate and a uniform stability bound that separates the one-sample sensitivity of the learned operator, and an algorithm-dependent dynamical gain. The latter can then be optimized, offering a tractable tool for certifying and comparing generalization capabilities of learning dynamics. We show that our results recover classical ones for gradient descent, apply naturally to momentum-based methods such as heavy-ball and Nesterov acceleration, and extend to data-driven control.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
Upper and lower bounds on the OBDD-width of a special integer multiplication
The $α$-Limit Problem: Convergence of a Linear Degenerate Interface Transmission Problem
Tight Maximin Share Guarantees of EFX and PMMS
Text-guided flow matching enables sample-efficient crystal structure generation
Parameter-Robust Subspace Correction with Multiple Semidefinite Penalties
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.