Conditional variance penalties and domain shift robustness

DOI10.1007/S10994-020-05924-1MaRDI QIDQ2051245zbMATH OpenOpenAlexFDO

Authors Christina Heinze-Deml, Nicolai Meinshausen

Publication date 24 November 2021

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1710.11469

zbMATH Keywords

distributional robustnessdataset shiftimage classificationcausal modelsanti-causal predictiondomain shift

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Domain-adversarial training of neural networks
• Robust domain adaptation
• scientific article; zbMATH DE number 6982327
• Can generalised divergences help for invariant neural networks?
• Robust unsupervised domain adaptation for neural networks via moment alignment

Cites work

• scientific article; zbMATH DE number 6982327 (Why is no real title available?)
• scientific article; zbMATH DE number 1909499 (Why is no real title available?)
• Causal inference by using invariant prediction: identification and confidence intervals. With discussion and authors' reply
• Causality. Models, reasoning, and inference
• Domain-adversarial training of neural networks
• Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
• Regularization via mass transportation
• Robust Regression and Lasso
• Semi-supervised learning in causal and anticausal settings
• Sliced Inverse Regression for Dimension Reduction
• The Probability Approach in Econometrics
• Variance-based regularization with convex objectives

Cited in

(6)

• scientific article; zbMATH DE number 7626776 (Why is no real title available?)
• Distributionally robust and generalizable inference
• Prominent roles of conditionally invariant components in domain adaptation: theory and algorithms
• Stabilizing variable selection and regression
• Environment invariant linear least squares
• Marginal singularity and the benefits of labels in covariate-shift

Describes a project that uses

Uses Software

• AlexNet
• Adam
• ImageNet
• TensorFlow

This page was built for publication: Conditional variance penalties and domain shift robustness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2051245)