paper-with-me

Papers

MARS: Masked Automatic Ranks Selection in Tensor Decompositions

2020-06-18 · Maxim Kodryan, Dmitry Kropotov, Dmitry Vetrov

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.

📄 PDF Abstract BibTeX arXiv:2006.10859

Code (1)

maxbourdon/mars 공식 구현 pytorch

Tasks

Tensor Decomposition

Similar Papers 제목 키워드 기반

Understanding the Rank of Tensor Networks via an Intuitive Example-Driven Approach

2025-07-14 · Wuyang Zhou, Giorgos Iacovides, Kriton Konstantinidis, Ilya Kisil 외 arxiv

Tensor Network (TN) decompositions have emerged as an indispensable tool in Big Data analytics owing to their ability to provide compact low-rank representations, thus alleviating the ``Curse of Dimensionality'' inherent…

Learning with tree tensor networks: complexity estimates and model selection

2020-07-02 · Bertrand Michel, Anthony Nouy

Tree tensor networks, or tree-based tensor formats, are prominent model classes for the approximation of high-dimensional functions in computational and data science. They correspond to sum-product neural networks with a…

Model SelectionQuantizationTensor Networks

Bayesian Low Rank Tensor Ring Model for Image Completion

2020-06-29 · Zhen Long, Ce Zhu, Jiani Liu, Yipeng Liu

Low rank tensor ring model is powerful for image completion which recovers missing entries in data acquisition and transformation. The recently proposed tensor ring (TR) based completion algorithms generally solve the lo…

Bayesian Inference

On embedding Lambek calculus into commutative categorial grammars

2020-05-20 · Sergey Slavnov

We consider tensor grammars, which are an example of \commutative" grammars, based on the classical (rather than intuitionistic) linear logic. They can be seen as a surface representation of abstract categorial grammars …

Translation

MARS: Magnitude-Aware Rank Statistics

2026-05-22 · Muhammad Rajabinasab, Afsaneh M. Nejad, Arthur Zimek arxiv

Comprehensive evaluation of machine learning models is the key to make sure that they perform as robustly and consistently as desired. In order to summarize the experimental results and pick a winner, Critical Difference…