REVIEW 3 cited by
Distributionally Robust Transfer Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Many existing transfer learning methods rely on leveraging information from source data that closely resembles the target data. However, this approach often overlooks valuable knowledge that may be present in different yet potentially related auxiliary samples. When dealing with a limited amount of target data and a diverse range of source models, our paper introduces a novel approach, Distributionally Robust Optimization for Transfer Learning (TransDRO), that breaks free from strict similarity constraints. TransDRO is designed to optimize the most adversarial loss within an uncertainty set, defined as a collection of target populations generated as a convex combination of source distributions that guarantee excellent prediction performances for the target data. TransDRO effectively bridges the realms of transfer learning and distributional robustness prediction models. We establish the identifiability of TransDRO and its interpretation as a weighted average of source models closest to the baseline model. We also show that TransDRO achieves a faster convergence rate than the model fitted with the target data. Our comprehensive numerical studies and analysis of multi-institutional electronic health records data using TransDRO further substantiate the robustness and accuracy of TransDRO, highlighting its potential as a powerful tool in transfer learning applications.
Forward citations
Cited by 3 Pith papers
-
Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
A representation-aware Wasserstein DRO framework that shrinks estimators toward an external representation subspace, with asymptotic inference and adaptive robustness tuning.
-
Sufficiency-principled Transfer Learning via Model Averaging
A sufficiency-penalized model averaging transfer learning method that adaptively selects informative domains, with convergence rates, optimality, and asymptotic normality.
-
When few labeled target data suffice: a theory of semi-supervised domain adaptation via fine-tuning from multiple adaptive starts
Under linear anticausal causal models, fine-tuning from UDA starts achieves target-label sample complexity proportional to the intervention dimension, not the ambient dimension.
Discussion (0). Sign in to comment.