Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization
Abstract
Domain Adaptation (DA) often lacks worst-case guarantees, while Distributionally Robust Optimization (DRO) based only on source data centers its ambiguity set at the source law and ignores available target structure. To bridge this gap, we introduce a doubly-anchored DRO framework whose ambiguity set is the intersection of ϕ-divergence balls centered at the source law and a source-completed target reference law, the latter pairing the target covariate law with the source conditional law. We derive dual-induced adversarial bridge geometries for symmetric and asymmetric divergence pairings, notably introducing a Kullback--Leibler/squared-Hellinger (KL/HD) bridge. This asymmetric formulation yields a Lambert-W geometry in which source-side exponential risk tilting and target-side Hellinger stabilization enter through distinct terms, attenuating, but not bounding, the effect of large likelihood ratios. Furthermore, without imposing covariate shift, we establish finite-sample generalization bounds for the minimizer of a structural, loss-agnostic density-bridge risk under bounded-overlap conditions; these bounds do not apply directly to the loss-aware DRO min--max estimator. We translate our framework into a bridge-weighted Nadaraya--Watson estimator, proving uniform consistency for the source regression function and pointwise asymptotic normality, with target recovery when the source and target regression functions coincide, as under covariate shift. Finally, an empirical evaluation on a domain-shifted Fashion-MNIST dataset illustrates the finite-sample stability of the asymmetric KL/HD bridge under severe synthetic target-covariate corruption.
Related
- Data-driven joint optimization of maintenance and spare parts provisioning: A distributionally robust approach
- Conformal-DRO: Distributionally Robust Optimization with Conformalized Ambiguity Set
- On tractability, complexity, and mixed-integer convex programming representability of distributionally favorable optimization
- Calibrating Ambiguity Set via Diagnostic Transport for Distributionally Robust Optimization
- Higher-Order Sensitivity Analysis of Wasserstein and Adapted Wasserstein Distributionally Robust Optimization Problems
BibTeX
@misc{kepplinger2026domain,
title = {{Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization}},
author = {David Kepplinger and Anand N. Vidyashankar},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.32730},
eprint = {2609.32730},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.32730},
}
RIS
TY - UNPB
TI - Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization
AU - David Kepplinger
AU - Anand N. Vidyashankar
PY - 2026
DA - 2026/09/26
PB - arXiv
DO - 10.48550/arxiv.2609.32730
UR - https://arxiv.org/abs/2609.32730
AB - Domain Adaptation (DA) often lacks worst-case guarantees, while Distributionally Robust Optimization (DRO) based only on source data centers its ambiguity set at the source law and ignores available target structure. To bridge this gap, we introduce a doubly-anchored DRO framework whose ambiguity set is the intersection of ϕ-divergence balls centered at the source law and a source-completed target reference law, the latter pairing the target covariate law with the source conditional law. We derive dual-induced adversarial bridge geometries for symmetric and asymmetric divergence pairings, notably introducing a Kullback--Leibler/squared-Hellinger (KL/HD) bridge. This asymmetric formulation yields a Lambert-W geometry in which source-side exponential risk tilting and target-side Hellinger stabilization enter through distinct terms, attenuating, but not bounding, the effect of large likelihood ratios. Furthermore, without imposing covariate shift, we establish finite-sample generalization bounds for the minimizer of a structural, loss-agnostic density-bridge risk under bounded-overlap conditions; these bounds do not apply directly to the loss-aware DRO min--max estimator. We translate our framework into a bridge-weighted Nadaraya--Watson estimator, proving uniform consistency for the source regression function and pointwise asymptotic normality, with target recovery when the source and target regression functions coincide, as under covariate shift. Finally, an empirical evaluation on a domain-shifted Fashion-MNIST dataset illustrates the finite-sample stability of the asymmetric KL/HD bridge under severe synthetic target-covariate corruption.
ER -