MARS: Masked Automatic Ranks Selection in Tensor Decompositions

Maxim Kodryan, Dmitry Kropotov, Dmitry Vetrov
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:3718-3732, 2023.

Abstract

Tensor decomposition methods have proven effective in various applications, including compression and acceleration of neural networks. At the same time, the problem of determining optimal decomposition ranks, which present the crucial parameter controlling the compressionaccuracy trade-off, is still acute. In this paper, we introduce MARS - a new efficient method for the automatic selection of ranks in general tensor decompositions. During training, the procedure learns binary masks over decomposition cores that “select” the optimal tensor structure. The learning is performed via relaxed maximum a posteriori (MAP) estimation in a specific Bayesian model and can be naturally embedded into the standard neural network training routine. Diverse experiments demonstrate that MARS achieves better results compared to previous works in various tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-kodryan23a, title = {MARS: Masked Automatic Ranks Selection in Tensor Decompositions}, author = {Kodryan, Maxim and Kropotov, Dmitry and Vetrov, Dmitry}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {3718--3732}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/kodryan23a/kodryan23a.pdf}, url = {https://proceedings.mlr.press/v206/kodryan23a.html}, abstract = {Tensor decomposition methods have proven effective in various applications, including compression and acceleration of neural networks. At the same time, the problem of determining optimal decomposition ranks, which present the crucial parameter controlling the compressionaccuracy trade-off, is still acute. In this paper, we introduce MARS - a new efficient method for the automatic selection of ranks in general tensor decompositions. During training, the procedure learns binary masks over decomposition cores that “select” the optimal tensor structure. The learning is performed via relaxed maximum a posteriori (MAP) estimation in a specific Bayesian model and can be naturally embedded into the standard neural network training routine. Diverse experiments demonstrate that MARS achieves better results compared to previous works in various tasks.} }
Endnote
%0 Conference Paper %T MARS: Masked Automatic Ranks Selection in Tensor Decompositions %A Maxim Kodryan %A Dmitry Kropotov %A Dmitry Vetrov %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-kodryan23a %I PMLR %P 3718--3732 %U https://proceedings.mlr.press/v206/kodryan23a.html %V 206 %X Tensor decomposition methods have proven effective in various applications, including compression and acceleration of neural networks. At the same time, the problem of determining optimal decomposition ranks, which present the crucial parameter controlling the compressionaccuracy trade-off, is still acute. In this paper, we introduce MARS - a new efficient method for the automatic selection of ranks in general tensor decompositions. During training, the procedure learns binary masks over decomposition cores that “select” the optimal tensor structure. The learning is performed via relaxed maximum a posteriori (MAP) estimation in a specific Bayesian model and can be naturally embedded into the standard neural network training routine. Diverse experiments demonstrate that MARS achieves better results compared to previous works in various tasks.
APA
Kodryan, M., Kropotov, D. & Vetrov, D.. (2023). MARS: Masked Automatic Ranks Selection in Tensor Decompositions. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:3718-3732 Available from https://proceedings.mlr.press/v206/kodryan23a.html.

Related Material