Co-Occurring Directions Sketching for Approximate Matrix Multiply

Youssef Mroueh, Etienne Marcheret, Vaibahava Goel
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:567-575, 2017.

Abstract

We introduce co-occurring directions sketching, a deterministic algorithm for approximate matrix product (AMM), in the streaming model. We show that co-occurring directions achieves a better error bound for AMM than other randomized and deterministic approaches for AMM. Co-occurring directions gives a (1 + epsilon) - approximation of the optimal low rank approximation of a matrix product. Empirically our algorithm outperforms competing methods for AMM, for a small sketch size. We validate empirically our theoretical findings and algorithms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v54-mroueh17a, title = {{Co-Occurring Directions Sketching for Approximate Matrix Multiply}}, author = {Mroueh, Youssef and Marcheret, Etienne and Goel, Vaibahava}, booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics}, pages = {567--575}, year = {2017}, editor = {Singh, Aarti and Zhu, Jerry}, volume = {54}, series = {Proceedings of Machine Learning Research}, month = {20--22 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v54/mroueh17a/mroueh17a.pdf}, url = {https://proceedings.mlr.press/v54/mroueh17a.html}, abstract = {We introduce co-occurring directions sketching, a deterministic algorithm for approximate matrix product (AMM), in the streaming model. We show that co-occurring directions achieves a better error bound for AMM than other randomized and deterministic approaches for AMM. Co-occurring directions gives a (1 + epsilon) - approximation of the optimal low rank approximation of a matrix product. Empirically our algorithm outperforms competing methods for AMM, for a small sketch size. We validate empirically our theoretical findings and algorithms.} }
Endnote
%0 Conference Paper %T Co-Occurring Directions Sketching for Approximate Matrix Multiply %A Youssef Mroueh %A Etienne Marcheret %A Vaibahava Goel %B Proceedings of the 20th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2017 %E Aarti Singh %E Jerry Zhu %F pmlr-v54-mroueh17a %I PMLR %P 567--575 %U https://proceedings.mlr.press/v54/mroueh17a.html %V 54 %X We introduce co-occurring directions sketching, a deterministic algorithm for approximate matrix product (AMM), in the streaming model. We show that co-occurring directions achieves a better error bound for AMM than other randomized and deterministic approaches for AMM. Co-occurring directions gives a (1 + epsilon) - approximation of the optimal low rank approximation of a matrix product. Empirically our algorithm outperforms competing methods for AMM, for a small sketch size. We validate empirically our theoretical findings and algorithms.
APA
Mroueh, Y., Marcheret, E. & Goel, V.. (2017). Co-Occurring Directions Sketching for Approximate Matrix Multiply. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 54:567-575 Available from https://proceedings.mlr.press/v54/mroueh17a.html.

Related Material