Unsupervised domain adaptation under hidden confounding
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916667005599744 |
|---|---|
| author | Meixide, Carlos García Insua, David Ríos |
| author_facet | Meixide, Carlos García Insua, David Ríos |
| contents | We introduce a new predictive mechanism that operates in the presence of hidden confounding across distributionally diverse data sources while ensuring consistent estimation of causal parameters-despite their recognized suboptimality for prediction in the literature. Our method is based on a novel estimand that captures the dependence structure between response noise and covariates, incorporating causal parameters into a generative model that adaptively replicates the conditional distribution of the test environment. Identifiability is achieved under a straightforward, empirically verifiable assumption. Our approach ensures probabilistic alignment with test distributions uniformly across arbitrary interventions, enabling valid predictions without requiring worst-case optimization or assumptions about the strength of perturbations at test time. Through extensive simulations, we demonstrate that our method outperforms state-of-the-art invariance-based and domain adaptation approaches. Additionally, we validate its practical applicability and superior target risk performance on a cardiovascular disease dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15502 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised domain adaptation under hidden confounding Meixide, Carlos García Insua, David Ríos Statistics Theory We introduce a new predictive mechanism that operates in the presence of hidden confounding across distributionally diverse data sources while ensuring consistent estimation of causal parameters-despite their recognized suboptimality for prediction in the literature. Our method is based on a novel estimand that captures the dependence structure between response noise and covariates, incorporating causal parameters into a generative model that adaptively replicates the conditional distribution of the test environment. Identifiability is achieved under a straightforward, empirically verifiable assumption. Our approach ensures probabilistic alignment with test distributions uniformly across arbitrary interventions, enabling valid predictions without requiring worst-case optimization or assumptions about the strength of perturbations at test time. Through extensive simulations, we demonstrate that our method outperforms state-of-the-art invariance-based and domain adaptation approaches. Additionally, we validate its practical applicability and superior target risk performance on a cardiovascular disease dataset. |
| title | Unsupervised domain adaptation under hidden confounding |
| topic | Statistics Theory |
| url | https://arxiv.org/abs/2402.15502 |