MARS: Masked Automatic Ranks Selection in Tensor Decompositions
This addresses a crucial bottleneck in tensor decomposition methods for applications like neural network compression, offering an incremental improvement over prior work.
The paper tackles the problem of determining optimal decomposition ranks for tensor decompositions, which control the compression-accuracy trade-off, by introducing MARS, a method that learns binary masks to automatically select ranks and achieves better results in diverse experiments.
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 compression-accuracy 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.