Individualized inference through fusion learning
Fusion learning methods, developed for the purpose of analyzing datasets from many different sources, have become a popular research topic in recent years. Individualized inference approaches through fusion learning extend fusion learning approaches to individualized inference problems over a hetero...
Gespeichert in:
Veröffentlicht in: | Wiley interdisciplinary reviews. Computational statistics 2020-09, Vol.12 (5), p.e1498-n/a |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Fusion learning methods, developed for the purpose of analyzing datasets from many different sources, have become a popular research topic in recent years. Individualized inference approaches through fusion learning extend fusion learning approaches to individualized inference problems over a heterogeneous population, where similar individuals are fused together to enhance the inference over the target individual. Both classical fusion learning and individualized inference approaches through fusion learning are established based on weighted aggregation of individual information, but the weight used in the latter is localized to the target individual. This article provides a review on two individualized inference methods through fusion learning, iFusion and iGroup, that are developed under different asymptotic settings. Both procedures guarantee optimal asymptotic theoretical performance and computational scalability.
This article is categorized under:
Statistical Learning and Exploratory Methods of the Data Sciences > Manifold Learning
Statistical Learning and Exploratory Methods of the Data Sciences > Modeling Methods
Statistical and Graphical Methods of Data Analysis > Nonparametric Methods
Data: Types and Structure > Massive Data
Prediction performance of individual Value‐at‐Risk estimation for S&P 500 stocks by aggregating other stocks with similar Fama‐French coefficients through individualized Group learning. The aggregation is controlled by a bandwidth parameter. The two limits at zero bandwidth and infinite bandwidth are equivalent to individual estimation and the classical fusion learning estimation, correspondingly. Our individualized fusion learning approach, by choosing the optimal bandwidth, has a superior performance than the other classical approaches. |
---|---|
ISSN: | 1939-5108 1939-0068 |
DOI: | 10.1002/wics.1498 |