Transfer Learning Under High-Dimensional Generalized Linear Models

• Published in: Journal of the American Statistical Association Vol. 118; no. 544; pp. 2684 - 2697
• Main Authors: Tian, Ye, Feng, Yang
• Format: Journal Article
• Language: English
• Published: United States Taylor & Francis 02.10.2023; Taylor & Francis Ltd
• Subjects: Algorithms; Americans; artificial intelligence; confidence interval; Error analysis; Generalized linear models; High-dimensional inference; Lasso; Learning; Linear analysis; linear models; Machine learning; Negative transfer; prediction; Sparsity; Statistical models; Statistics; Transfer learning; transfer learning; high-dimensional inference; sparsity; Lasso; Generalized linear models; negative transfer

In this work, we study the transfer learning problem under high-dimensional generalized linear models (GLMs), which aim to improve the fit on target data by borrowing information from useful source data. Given which sources to transfer, we propose a transfer learning algorithm on GLM, and derive its...