# On Localized Discrepancy for Domain Adaptation

arXiv: https://arxiv.org/abs/2008.06242 · HTML: https://mlsanity.com/paper/2008.06242/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2020.

## Built on by (most cited first, 14 of 14)

- [Discrepancy-Based Active Learning for Domain Adaptation](https://mlsanity.com/paper/2103.03757/) (2021)
- [Domain Adaptation meets Individual Fairness. And they get along](https://mlsanity.com/paper/2205.00504/) (2022)
- [Reliable learning in challenging environments](https://mlsanity.com/paper/2304.03370/) (2023)
- [Efficient Discrepancy Testing for Learning with Distribution Shift](https://mlsanity.com/paper/2406.09373/) (2024)
- [Best-Effort Adaptation](https://mlsanity.com/paper/2305.05816/) (2023)
- [On f-Divergence Principled Domain Adaptation: An Improved Framework](https://mlsanity.com/paper/2402.01887/) (2024)
- [Semi-Supervised Domain Adaptation with Auto-Encoder via Simultaneous Learning](https://mlsanity.com/paper/2210.09486/) (2022)
- [CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift](https://mlsanity.com/paper/2305.18458/) (2023)
- [Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization](https://mlsanity.com/paper/2203.05076/) (2022)
- [On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space](https://mlsanity.com/paper/2302.12351/) (2023)
- [Practicality of generalization guarantees for unsupervised domain adaptation with neural networks](https://mlsanity.com/paper/2303.08720/) (2023)
- [Differentially Private Domain Adaptation with Theoretical Guarantees](https://mlsanity.com/paper/2306.08838/) (2023)
- [Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation](https://mlsanity.com/paper/2504.16474/) (2025)
- [Beyond Discrepancy: Oracle Drift in Nonstationary Weighted Risk Minimization](https://mlsanity.com/paper/2610.13598/) (2026)

## Abstract (arXiv)

We propose the discrepancy-based generalization theories for unsupervised domain adaptation. Previous theories introduced distribution discrepancies defined as the supremum over complete hypothesis space. The hypothesis space may contain hypotheses that lead to unnecessary overestimation of the risk bound. This paper studies the localized discrepancies defined on the hypothesis space after localization. First, we show that these discrepancies have desirable properties. They could be significantly smaller than the pervious discrepancies. Their values will be different if we exchange the two domains, thus can reveal asymmetric transfer difficulties. Next, we derive improved generalization bounds with these discrepancies. We show that the discrepancies could influence the rate of the sample complexity. Finally, we further extend the localized discrepancies for achieving super transfer and derive generalization bounds that could be even more sample-efficient on source domain.