Research map / Learning theory and algorithms / Prediction and decision losses
Algorithms and Theory for Multiple-Source Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 distribution-weighted combination instead of uniform combination | SVR source predictors · Sentiment analysis (KDBE) | MSE: 1.74$\pm$0.04 -> 1.61$\pm$0.04 | Helped |
| Use distribution-weighted combination instead of KMM adaptation | SVR source predictors · Sentiment analysis (KDBE) | MSE: 1.82$\pm$0.06 -> 1.61$\pm$0.04 | Helped |
| Use distribution-weighted combination instead of uniform combination | CNN source predictors · Digit recognition (mean) | accuracy: 84.0 -> 94.7 | Helped |
| Use distribution-weighted combination instead of joint training | CNN source predictors · Digit recognition (mean) | accuracy: 94.6 -> 94.7 | No clear effect |
| Use distribution-weighted combination instead of uniform combination | AlexNet source predictors · Office (mean) | accuracy: 81.6 $\pm$ 0.5 -> 84.7 $\pm$ 0.5 | Helped |
| Use distribution-weighted combination instead of joint training | AlexNet source predictors · Office (mean) | accuracy: 83.6 $\pm$ 0.4 -> 84.7 $\pm$ 0.5 | Helped |
Closest papers by meaning
- CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions (NeurIPS 2024 · similarity 0.86)
- Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation (ICML 2025 · similarity 0.85)
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.84)
- A Theory for Conditional Generative Modeling on Multiple Data Sources (ICML 2025 · similarity 0.84)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.84)
- RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts (ICML 2025 · similarity 0.83)
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.