AI Paper Atlas

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

NeurIPS 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 2 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
BPDA instead of IWV for parameter choiceMMD · Transformed Moonsaverage target misclassification error: 0.20 -> 0.16Improved
BPDA instead of DEV for parameter choiceMMD · Transformed Moonsaverage target misclassification error: 0.34 -> 0.16Improved
BPDA instead of IWV for parameter choiceDANN · Transformed Moonsaverage target misclassification error: 0.18 -> 0.12Improved
BPDA instead of DEV for parameter choiceDANN · Transformed Moonsaverage target misclassification error: 0.17 -> 0.12Improved
BPDA instead of DEV for parameter choiceCMD · Transformed Moonsaverage target misclassification error: 0.19 -> 0.19No clear effect
BPDA instead of IWV for parameter choiceCMD · Transformed Moonsaverage target misclassification error: 0.20 -> 0.19No clear effect
BPDA instead of source-only trainingaverage over MMD, DANN, CMD · Transformed Moonsaverage target misclassification error: 0.20 -> 0.16Improved
BPDA instead of IWV for parameter choiceMMD · Amazon Reviewsaverage target misclassification error: 0.25 -> 0.22Improved
BPDA instead of DEV for parameter choiceDANN · Amazon Reviewsaverage target misclassification error: 0.32 -> 0.27Improved
BPDA instead of IWV for parameter choiceDANN · Amazon Reviewsaverage target misclassification error: 0.28 -> 0.27No clear effect
BPDA instead of IWV for parameter choiceCMD · Amazon Reviewsaverage target misclassification error: 0.24 -> 0.21Improved
BPDA instead of DEV for parameter choiceaverage over MMD, DANN, CMD · Amazon Reviewsaverage target misclassification error: 0.27 -> 0.23Improved

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