Research map / Label-efficient and robust learning / Domain adaptation and generalization
The balancing principle for parameter choice in distance-regularized domain adaptation
Werner Zellinger, Natalia Shepeleva, Marius-Constantin Dinu, Hamid Eghbal-zadeh, Hoan Duc Nguyen, Bernhard Nessler, Sergei Pereverzyev, Bernhard A. Moser
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| BPDA instead of IWV for parameter choice | MMD · Transformed Moons | average target misclassification error: 0.20 -> 0.16 | Improved |
| BPDA instead of DEV for parameter choice | MMD · Transformed Moons | average target misclassification error: 0.34 -> 0.16 | Improved |
| BPDA instead of IWV for parameter choice | DANN · Transformed Moons | average target misclassification error: 0.18 -> 0.12 | Improved |
| BPDA instead of DEV for parameter choice | DANN · Transformed Moons | average target misclassification error: 0.17 -> 0.12 | Improved |
| BPDA instead of DEV for parameter choice | CMD · Transformed Moons | average target misclassification error: 0.19 -> 0.19 | No clear effect |
| BPDA instead of IWV for parameter choice | CMD · Transformed Moons | average target misclassification error: 0.20 -> 0.19 | No clear effect |
| BPDA instead of source-only training | average over MMD, DANN, CMD · Transformed Moons | average target misclassification error: 0.20 -> 0.16 | Improved |
| BPDA instead of IWV for parameter choice | MMD · Amazon Reviews | average target misclassification error: 0.25 -> 0.22 | Improved |
| BPDA instead of DEV for parameter choice | DANN · Amazon Reviews | average target misclassification error: 0.32 -> 0.27 | Improved |
| BPDA instead of IWV for parameter choice | DANN · Amazon Reviews | average target misclassification error: 0.28 -> 0.27 | No clear effect |
| BPDA instead of IWV for parameter choice | CMD · Amazon Reviews | average target misclassification error: 0.24 -> 0.21 | Improved |
| BPDA instead of DEV for parameter choice | average over MMD, DANN, CMD · Amazon Reviews | average target misclassification error: 0.27 -> 0.23 | Improved |
Closest papers by meaning
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.88)
- Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation (ICLR 2023 · similarity 0.87)
- Unsupervised Domain Adaptation With Similarity Learning (CVPR 2018 · similarity 0.87)
- Domain Adaptation with Adaptive $f$-Divergence: Tighter Variational Representation and Generalization Bounds (ICML 2026 · similarity 0.87)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.86)
- On $f$-Divergence Principled Domain Adaptation: An Improved Framework (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
