Asymptotic and non-Asymptotic Rate-Loss Bounds for Linear Regression with Side Information - IMT Atlantique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Asymptotic and non-Asymptotic Rate-Loss Bounds for Linear Regression with Side Information

Résumé

In the framework of goal-oriented communications, this paper investigates the fundamental achievable rate-loss function of a learning task performed on compressed data. It considers the setup where the data, collected remotely, are compressed and sent over a noiseless channel to a server that aims at applying linear regression on compressed data and side information. The paper contributions are threefold: i) the rateloss region is first derived in the asymptotic regime, i.e., when the length of the source tends to infinity, (ii) the tradeoff between data reconstruction and linear regression is investigated from the asymptotic rate-loss region, and iii) the approach is extended to the finite blocklength regime.
Fichier principal
Vignette du fichier
Eusipco_CoLearn.pdf (287.41 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04184061 , version 1 (21-08-2023)

Identifiants

Citer

Jiahui Wei, Elsa Dupraz, Philippe Mary. Asymptotic and non-Asymptotic Rate-Loss Bounds for Linear Regression with Side Information. EUSIPCO 2023: 31st European Signal Processing Conference, Sep 2023, Helsinki, Finland. pp.1275, ⟨10.23919/EUSIPCO58844.2023.10289952⟩. ⟨hal-04184061⟩
25 Consultations
18 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More