Finite Sample Analysis of a Data-Driven Estimator
IEEE Signal Processing Letters · 2026 · 33 · 2475-2479
DOI: 10.1109/lsp.2026.3702913 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Braghadeesh Lakshminarayanan und 1 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vetenskapsrådet, Wallenberg AI, Autonomous Systems and Software Program, Swedish Civil Defence and Resilience Agency.
Abstract (Originalsprache)
Over the past decade, new types of estimators have been developed in statistics, signal processing and system identification, which apply tools from supervised learning, such as deep neural networks or kernel regression on synthetic data. In spite of their competitive performance, a systematic finite-sample analysis of these so-called data-driven estimators is still missing. In this letter, we take first steps in this direction by deriving finite-sample bounds for a specific data-driven estimator, known as the Two-Stage method. The derived bounds hold under fairly general conditions, and highlight the effect of different user choices involved in the construction of this estimator.
Förderung
- Vetenskapsrådet
- Wallenberg AI, Autonomous Systems and Software Program
- Swedish Civil Defence and Resilience Agency
Zitieren
APA
Lakshminarayanan, B., & Rojas, C. R. (2026). Finite Sample Analysis of a Data-Driven Estimator. IEEE Signal Processing Letters, 33, 2475-2479. https://doi.org/10.1109/lsp.2026.3702913
Vancouver
Lakshminarayanan B, Rojas CR. Finite Sample Analysis of a Data-Driven Estimator. IEEE Signal Processing Letters. 2026;33:2475-2479. doi:10.1109/lsp.2026.3702913
BibTeX
@article{Lakshminarayanan2026,
author = {Lakshminarayanan, Braghadeesh and Rojas, Cristian R.},
title = {Finite Sample Analysis of a Data-Driven Estimator},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {2475--2479},
doi = {10.1109/lsp.2026.3702913}
}
EUVIMED