Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Generalization by Marginal Transfer Learning
Gilles Blanchard, Aniket Anand Deshmukh, Urun Dogan, Gyemin Lee, Clayton Scott
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 |
|---|---|---|---|
| use marginal transfer learning (kernel on the task marginal distribution) instead of pooling all tasks | SVM domain generalization · synthetic ellipse tasks (N in {16,64,256}, n in {8,16,32,256}) | classification error | Improved |
| increase number of tasks N and examples per task n (ablation) | marginal transfer learning · synthetic ellipse tasks | classification error | Improved |
| increase N and n for the pooling baseline (ablation) | pooling SVM · synthetic ellipse tasks | classification error | No clear effect |
| use a multi-task kernel instead of the marginal transfer kernel | domain generalization SVM · real-world data sets | classification error | Hurt |
Closest papers by meaning
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.91)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · similarity 0.90)
- Improving Domain Generalization with Domain Relations (ICLR 2024 · similarity 0.89)
- Set Valued Predictions For Robust Domain Generalization (ICML 2025 · similarity 0.89)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.89)
- Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains (AAAI 2024 · similarity 0.88)
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.
