• Mon espace de travail
  • Aide IRIS
  • Par Publication Par Personne Par Unité
    • English
    • Français
  • Se connecter
Logo du site

IRIS | Système d’Information de la Recherche Institutionnelle

  • Accueil
  • Personnes
  • Publications
  • Unités
  • Périodiques
UNIL
  • English
  • Français
Se connecter
IRIS
  • Accueil
  • Personnes
  • Publications
  • Unités
  • Périodiques
  • Mon espace de travail
  • Aide IRIS

Parcourir IRIS

  • Par Publication
  • Par Personne
  • Par Unité
  1. Accueil
  2. IRIS
  3. Publication
  4. Statistical Quantile Learning for Large, Nonlinear, and Additive Latent Variable Models.
 
  • Détails
Titre

Statistical Quantile Learning for Large, Nonlinear, and Additive Latent Variable Models.

Type
autre
Institution
UNIL/CHUV/Unisanté + institutions partenaires
Auteur(s)
Bodelet, Julien
Auteure/Auteur
Blanc, Guillaume
Auteure/Auteur
Shan, Jiajun
Auteure/Auteur
Terrera, Graciela M.
Auteure/Auteur
Chén, Oliver Y
Auteure/Auteur
Liens vers les personnes
Chen, Oliver Yibing  
Liens vers les unités
Immunologie et allergie  
Date de publication
2023-12-29
Langue
anglais
Résumé
The studies of large-scale, high-dimensional data in fields such as genomics and neuroscience have injected new insights into science. Yet, despite advances, they are confronting several chal- lenges, often simultaneously: lack of interpretability, nonlinearity, slow computation, inconsistency and uncertain convergence, and small sample sizes compared to high feature dimensions. Here, we propose a relatively simple, scalable, and consistent nonlinear dimension reduction method that can potentially address these issues in unsupervised settings. We call this method Statistical Quantile Learning (SQL) because, methodologically, it leverages on a quantile approximation of the latent variables together with standard nonparametric techniques (sieve or penalyzed methods). We show that estimating the model simplifies into a convex assignment matching problem; we derive its asymptotic properties; we show that the model is identifiable under few conditions. Compared to its linear competitors, SQL explains more variance, yields better separation and explanation, and delivers more accurate outcome prediction. Compared to its nonlinear competitors, SQL shows considerable advantage in interpretability, ease of use and computations in large-dimensional set- tings. Finally, we apply SQL to high-dimensional gene expression data (consisting of 20, 263 genes from 801 subjects), where the proposed method identified latent factors predictive of five cancer types. The SQL package is available at https://github.com/jbodelet/SQL.
Sujets

High-dimensionality

Nonlinear model

Latent variable model...

Generative models

Dimension reduction

GAN

VAE

Nonparametric estimat...

Assignment Matching

Prediction.

PID Serval
serval:BIB_0622E4AB21A0
DOI
10.48550/arXiv.2003.13119
Permalien
https://iris.unil.ch/handle/iris/33929
Date de création
2024-01-11T17:05:38.584Z
Date de création dans IRIS
2025-05-20T13:23:45Z
Fichier(s)
En cours de chargement...
Vignette d'image
Nom

SQL.pdf

Version du manuscrit

preprint

Taille

2.91 MB

Format

Adobe PDF

PID Serval

serval:BIB_0622E4AB21A0.P001

URN

urn:nbn:ch:serval-BIB_0622E4AB21A04

Somme de contrôle

(MD5):aad417aab9bac6489ba57770c89e5e22

  • Copyright © 2024 UNIL
  • Informations légales