Saved in:
Bibliographic Details
Main Authors: Metakalard, Abdelkader, Lauer, Fabien, Colin, Kevin, Gilson, Marion
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.15586
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917277981474816
author Metakalard, Abdelkader
Lauer, Fabien
Colin, Kevin
Gilson, Marion
author_facet Metakalard, Abdelkader
Lauer, Fabien
Colin, Kevin
Gilson, Marion
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15586
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Uniform error bounds for quantized dynamical models
Metakalard, Abdelkader
Lauer, Fabien
Colin, Kevin
Gilson, Marion
Machine Learning
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.
title Uniform error bounds for quantized dynamical models
topic Machine Learning
url https://arxiv.org/abs/2602.15586