stat.MLNov 16, 2026

High-dimensional transfer learning with unaligned ordinal responses

Authors: Ruopei Fu, Ying Yang

Organizations: Department of Mathematical Sciences, Tsinghua University · Department of Statistics and Data Science, Tsinghua University

Abstract

In this work, we study high-dimensional transfer learning with unaligned ordinal responses, allowing different domain-specific regression coefficients, cumulative links and thresholds. We develop the sample-split and full-target algorithms that pool source and target likelihoods and then estimate a target correction. Under suitable conditions, our algorithms achieve minimax-optimal rates for parameter estimation and excess risk. Simulations favor the full-target algorithm over the sample-split algorithm for finite-sample estimation and prediction. An application to a medical dataset further demonstrates the predictive gains of our full-target algorithm over the target-only and pooled baselines when transferring information from the five-category source data to binary hospital mortality.

Explore similar work

CardsList
  1. Transfer Learning Through Conditional Quantile Matching

    Feb 2, 2026Yikun Zhang, Steven Wilkins-Reeves, Wesley Lee +1Transfer LearningMulti-Source Domain Adaptation

  2. Harnessing Source Heterogeneity for Cluster-Structured Transfer Learning

    Jun 3, 2026Xiaohui Yin, Jun Jin, Shane J. Sacco +2Cross-Domain Transfer LearningTransfer Learning