Hybrid Discriminative-Generative Approaches with Gaussian Processes

Ricardo Andrade-PachecoJames HensmanNeil D. Lawrence
Proceedings of the Seventeenth International Workshop on Artificial Intelligence and Statistics, JMLR W\&CP 33 33:47-56, 2014.

Abstract

Machine learning practitioners are often faced with a choice between a discriminative and a generative approach to modelling. Here, we present a model based on a hybrid approach that breaks down some of the barriers between the discriminative and generative points of view, allowing continuous dimensionality reduction of hybrid discrete-continous data, discriminative classification with missing inputs and manifold learning informed by class labels.

Cite this Paper


BibTeX
@InProceedings{Andrade:hybrid14, title = {Hybrid Discriminative-Generative Approaches with Gaussian Processes}, author = {Ricardo Andrade-Pacheco and James Hensman and Neil D. Lawrence}, booktitle = {Proceedings of the Seventeenth International Workshop on Artificial Intelligence and Statistics}, pages = {47--56}, year = {2014}, editor = {Sami Kaski and Jukka Corander}, volume = {33}, address = {Iceland}, publisher = {JMLR W\&CP 33}, abstract = {Machine learning practitioners are often faced with a choice between a discriminative and a generative approach to modelling. Here, we present a model based on a hybrid approach that breaks down some of the barriers between the discriminative and generative points of view, allowing continuous dimensionality reduction of hybrid discrete-continous data, discriminative classification with missing inputs and manifold learning informed by class labels.} }
Endnote
%0 Conference Paper %T Hybrid Discriminative-Generative Approaches with Gaussian Processes %A Ricardo Andrade-Pacheco %A James Hensman %A Neil D. Lawrence %B Proceedings of the Seventeenth International Workshop on Artificial Intelligence and Statistics %D 2014 %E Sami Kaski %E Jukka Corander %F Andrade:hybrid14 %I JMLR W\&CP 33 %P 47--56 %V 33 %X Machine learning practitioners are often faced with a choice between a discriminative and a generative approach to modelling. Here, we present a model based on a hybrid approach that breaks down some of the barriers between the discriminative and generative points of view, allowing continuous dimensionality reduction of hybrid discrete-continous data, discriminative classification with missing inputs and manifold learning informed by class labels.
RIS
TY - CPAPER TI - Hybrid Discriminative-Generative Approaches with Gaussian Processes AU - Ricardo Andrade-Pacheco AU - James Hensman AU - Neil D. Lawrence BT - Proceedings of the Seventeenth International Workshop on Artificial Intelligence and Statistics DA - 2014/01/01 ED - Sami Kaski ED - Jukka Corander ID - Andrade:hybrid14 PB - JMLR W\&CP 33 VL - 33 SP - 47 EP - 56 AB - Machine learning practitioners are often faced with a choice between a discriminative and a generative approach to modelling. Here, we present a model based on a hybrid approach that breaks down some of the barriers between the discriminative and generative points of view, allowing continuous dimensionality reduction of hybrid discrete-continous data, discriminative classification with missing inputs and manifold learning informed by class labels. ER -
APA
Andrade-Pacheco, R., Hensman, J. & Lawrence, N.D.. (2014). Hybrid Discriminative-Generative Approaches with Gaussian Processes. Proceedings of the Seventeenth International Workshop on Artificial Intelligence and Statistics 33:47-56

Related Material