Transfer Learning for Classification under Decision Rule Drift with Application to Optimal Individualized Treatment Rule Estimation

2025-08-28

AI Summary

Estimating individualized treatment rules (ITRs) under decision rule drift—where optimal treatment policies shift across domains—remains challenging due to distributional shifts in covariates and outcomes. Method: This paper pioneers the extension of transfer learning from regression function modeling to ITR estimation. We propose a Bayesian decision boundary geometric transformation framework that models posterior probability drift, performs low-dimensional empirical risk minimization, and integrates regularization with consistency analysis to enable robust cross-domain knowledge transfer. Contribution/Results: We establish theoretical consistency of the estimator and derive an upper bound on its excess risk. Extensive experiments on synthetic and real-world clinical datasets demonstrate that our method significantly improves stability, interpretability, and estimation accuracy under distributional shift, outperforming existing ITR estimation approaches.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Reasoning under Uncertainty: Sequential Decision Making
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

In this paper, we extend the transfer learning classification framework from regression function-based methods to decision rules. We propose a novel methodology for modeling posterior drift through Bayes decision rules. By exploiting the geometric transformation of the Bayes decision boundary, our method reformulates the problem as a low-dimensional empirical risk minimization problem. Under mild regularity conditions, we establish the consistency of our estimators and derive the risk bounds. Moreover, we illustrate the broad applicability of our method by adapting it to the estimation of optimal individualized treatment rules. Extensive simulation studies and analyses of real-world data further demonstrate both superior performance and robustness of our approach.

Problem

• Extending transfer learning to decision rule classification
• Modeling posterior drift via Bayes decision rules
• Estimating optimal individualized treatment rules

Innovation

• Transfer learning for decision rule drift
• Bayes decision boundary geometric transformation
• Low-dimensional empirical risk minimization