Show simple item record

dc.contributor.authorCilingir, Kubraen_US
dc.contributor.authorManzelli, Rachelen_US
dc.contributor.authorKulis, Brianen_US
dc.date.accessioned2021-09-16T13:59:29Z
dc.date.available2021-09-16T13:59:29Z
dc.date.issued2020-07-12
dc.identifier.citationKubra Cilingir, Rachel Manzelli, Brian Kulis. 2020. "Deep Divergence Learning." Proc. International Conference on Machine Learning
dc.identifier.urihttps://hdl.handle.net/2144/43021
dc.description.abstractClassical linear metric learning methods have recently been extended along two distinct lines: deep metric learning methods for learning embeddings of the data using neural networks, and Bregman divergence learning approaches for extending learning Euclidean distances to more general divergence measures such as divergences over distributions. In this paper, we introduce deep Bregman divergences, which are based on learning and parameterizing functional Bregman divergences using neural networks, and which unify and extend these existing lines of work. We show in particular how deep metric learning formulations, kernel metric learning, Mahalanobis metric learning, and moment-matching functions for comparing distributions arise as special cases of these divergences in the symmetric setting. We then describe a deep learning framework for learning general functional Bregman divergences, and show in experiments that this method yields superior performance on benchmark datasets as compared to existing deep metric learning approaches. We also discuss novel applications, including a semi-supervised distributional clustering problem, and a new loss function for unsupervised data generation.en_US
dc.language.isoen_US
dc.rightsCopyright 2020 by the author(s).en_US
dc.titleDeep divergence learningen_US
dc.typeConference materialsen_US
dc.description.versionPublished versionen_US
pubs.elements-sourcemanual-entryen_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Engineeringen_US
pubs.organisational-groupBoston University, College of Engineering, Department of Electrical & Computer Engineeringen_US
pubs.publication-statusPublisheden_US
dc.identifier.mycv615084


This item appears in the following Collection(s)

Show simple item record