Seonghwi Kim

2 accepted papers

2026

Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation

Seonghwi Kim, Sung Ho Jo, Wooseok Ha, Minwoo Chae

ICLR 2026poster

Unsupervised domain adaptation (UDA) is a statistical learning problem when the distribution of training (source) data is different from that of test (target) data. In this setting, one has access to labeled data only from the source domain and unlabeled data from the target domain. The central obje…

Cited by 0 Source ↗Scholar ↗

2026

Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets

Sung Ho Jo, Seonghwi Kim, Minwoo Chae

ICLR 2026poster

Conventional supervised learning methods are often vulnerable to spurious correlations, particularly under distribution shifts in test data. To address this issue, several approaches, most notably Group DRO, have been developed. While these methods are highly robust to subpopulation or group shifts,…

Cited by 0 Source ↗Scholar ↗