Sparse Multi-Prototype Classification

Vikas K. Garg, Lin Xiao, Ofer Dekel
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:703-713, 2018.

Abstract

We introduce a new class of sparse multi- prototype classifiers, designed to combine the computational advantages of sparse predictors with the non-linear power of prototype-based classification techniques. This combination makes sparse multi- prototype models especially well-suited for resource constrained computational plat- forms, such as the IoT devices. We cast our supervised learning problem as a convex- concave saddle point problem and design a provably-fast algorithm to solve it. We complement our theoretical analysis with an empirical study that demonstrates the merits of our methodology.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-garg18a, title = {Sparse Multi-Prototype Classification}, author = {Garg, Vikas K. and Xiao, Lin and Dekel, Ofer}, booktitle = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {703--713}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/garg18a/garg18a.pdf}, url = {https://proceedings.mlr.press/r16/garg18a.html}, abstract = {We introduce a new class of sparse multi- prototype classifiers, designed to combine the computational advantages of sparse predictors with the non-linear power of prototype-based classification techniques. This combination makes sparse multi- prototype models especially well-suited for resource constrained computational plat- forms, such as the IoT devices. We cast our supervised learning problem as a convex- concave saddle point problem and design a provably-fast algorithm to solve it. We complement our theoretical analysis with an empirical study that demonstrates the merits of our methodology.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Sparse Multi-Prototype Classification %A Vikas K. Garg %A Lin Xiao %A Ofer Dekel %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-garg18a %I PMLR %P 703--713 %U https://proceedings.mlr.press/r16/garg18a.html %V R16 %X We introduce a new class of sparse multi- prototype classifiers, designed to combine the computational advantages of sparse predictors with the non-linear power of prototype-based classification techniques. This combination makes sparse multi- prototype models especially well-suited for resource constrained computational plat- forms, such as the IoT devices. We cast our supervised learning problem as a convex- concave saddle point problem and design a provably-fast algorithm to solve it. We complement our theoretical analysis with an empirical study that demonstrates the merits of our methodology. %Z Reissued by PMLR on 04 October 2026.
APA
Garg, V.K., Xiao, L. & Dekel, O.. (2018). Sparse Multi-Prototype Classification. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:703-713 Available from https://proceedings.mlr.press/r16/garg18a.html. Reissued by PMLR on 04 October 2026.

Related Material