The Role of Embedding Complexity in Domain-invariant RepresentationsDownload PDF

Anonymous

16 May 2019 (modified: 22 Oct 2023)AMTL 2019Readers: Everyone
Keywords: domain adaptation, domain-invariant representations, model complexity, theory, deep learning
TL;DR: A general upper bound on the target domain's risk that reflects the role of embedding-complexity.
Abstract: Unsupervised domain adaptation aims to generalize the hypothesis trained in a source domain to an unlabeled target domain. One popular approach to this problem is to learn a domain-invariant representation for both domains. In this work, we study, theoretically and empirically, the explicit effect of the embedding on generalization to the target domain. In particular, the complexity of the class of embeddings affects an upper bound on the target domain's risk. This is reflected in our experiments, too.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1910.05804/code)
0 Replies

Loading