Can I read Domain Generalization via Invariant Feature Representation on EtoBox?

Domain Generalization via Invariant Feature Representation by Muandet, Krikamol; Balduzzi, David; Schölkopf, Bernhard is a scholarly article available to read on EtoBox.

What is Domain Generalization via Invariant Feature Representation about?

This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Domain-Invariant Component Analysis (DICA), a kernel-based optimization algorithm that learns an invariant transformation by minimizing the dissimilarity across domains, whilst preserving the functional relationship between input and output variables. A learning-theoretic analysis shows that reducing dissimilarity improves the expected generalization ability of classifiers on new domains, motivating the proposed algorithm. Experimental results on synthetic and real-world datasets demonstrate that DICA successfully learns invariant features and improves classifier performance in practice.

Author

Muandet, Krikamol; Balduzzi, David; Schölkopf, Bernhard

Published

2013

Language

EN