AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation

Yuyang Deng, Ilja Kuzborskij, Mehrdad Mahdavi

NeurIPS 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
weighted ERM with learned mixture weights instead of average-weight ERMOur method · MNIST target Group 1accuracy: 69.9 -> 80.0Improved
weighted ERM with learned weights instead of average ERMOur method · MNIST target Group 2accuracy: 40.0 -> 69.9Improved
weighted ERM with learned weights instead of average ERMOur method · MNIST target Group 3accuracy: 34.9 -> 55.0Improved
weighted ERM with learned weights instead of average ERMOur method · MNIST target mix of Group 1 and 2accuracy: 59.9 -> 65.0Improved
use source data with learned weights instead of training only on target dataOur method · MNIST target Group 2accuracy: 55.0 -> 69.9Improved
use source data with learned weights instead of training only on target dataOur method · MNIST target Group 1accuracy: 69.9 -> 80.0Improved
pure target training instead of average ERMPure target training · MNIST target mix of Group 1 and 2accuracy: 59.9 -> 55.0Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy