Uniform error bounds for quantized dynamical models

📅 2026-02-17
📈 Citations: 0
Influential: 0
📄 PDF

career value

215K/year
🤖 AI Summary
This work addresses the challenge of evaluating generalization performance in quantized dynamical system identification, where data dependence and non-ideal optimization complicate theoretical analysis. The authors propose a unified framework for statistical error bounds, leveraging a block decomposition technique to derive slow-rate bounds and introducing a novel subsampled interval strategy to establish fast-rate, variance-adaptive bounds. These bounds explicitly link the number of bits used for model quantization to statistical complexity. Notably, this is the first study to incorporate hardware constraints—such as quantization bitwidth—into generalization error theory, offering theoretically grounded, interpretable, and practically actionable guarantees for real-world applications including quantized modeling and hybrid system identification.

Technology Category

Application Category

📝 Abstract
This paper provides statistical guarantees on the accuracy of dynamical models learned from dependent data sequences. Specifically, we develop uniform error bounds that apply to quantized models and imperfect optimization algorithms commonly used in practical contexts for system identification, and in particular hybrid system identification. Two families of bounds are obtained: slow-rate bounds via a block decomposition and fast-rate, variance-adaptive, bounds via a novel spaced-point strategy. The bounds scale with the number of bits required to encode the model and thus translate hardware constraints into interpretable statistical complexities.
Problem

Research questions and friction points this paper is trying to address.

quantized dynamical models
uniform error bounds
dependent data
system identification
hybrid systems
Innovation

Methods, ideas, or system contributions that make the work stand out.

uniform error bounds
quantized dynamical models
dependent data
spaced-point strategy
hybrid system identification
🔎 Similar Papers
2024-02-05International Symposium on Information TheoryCitations: 5
A
Abdelkader Metakalard
Université de Lorraine, CNRS, CRAN, F-54000 Nancy, France
F
Fabien Lauer
Université de Lorraine, CNRS, LORIA, F-54000 Nancy, France
K
Kevin Colin
Université de Lorraine, CNRS, CRAN, F-54000 Nancy, France
M
Marion Gilson
Université de Lorraine, CNRS, CRAN, F-54000 Nancy, France