paper-with-me

홈 › Papers

Many-body Approximation for Non-negative Tensors

2022-09-30 · NeurIPS 2023 11

We present an alternative approach to decompose non-negative tensors, called many-body approximation. Traditional decomposition methods assume low-rankness in the representation, resulting in difficulties in global optimization and target rank selection. We avoid these problems by energy-based modeling of tensors, where a tensor and its mode correspond to a probability distribution and a random variable, respectively. Our model can be globally optimized in terms of the KL divergence minimization by taking the interaction between variables (that is, modes), into account that can be tuned more intuitively than ranks. Furthermore, we visualize interactions between modes as tensor networks and reveal a nontrivial relationship between many-body approximation and low-rank approximation. We demonstrate the effectiveness of our approach in tensor completion and approximation.

📄 PDF Abstract BibTeX arXiv:2209.15338

Code (0)

등록된 구현이 없습니다.

Tasks

global-optimizationTensor Networks

Similar Papers 제목 키워드 기반

Fast Tucker Rank Reduction for Non-Negative Tensors Using Mean-Field Approximation

2021-03-04 · NeurIPS 2021 12 · Kazu Ghalamkari, Mahito Sugiyama

We present an efficient low-rank approximation algorithm for non-negative tensors. The algorithm is derived from our two findings: First, we show that rank-1 approximation for tensors can be viewed as a mean-field approx…

Tensor Decomposition

Error Analysis of Tensor-Train Cross Approximation

2022-07-09 · Zhen Qin, Alexander Lidiak, Zhexuan Gong, Gongguo Tang 외

Tensor train decomposition is widely used in machine learning and quantum physics due to its concise representation of high-dimensional tensors, overcoming the curse of dimensionality. Cross approximation-originally deve…

Nonnegative Low Rank Tensor Approximation and its Application to Multi-dimensional Images

2020-07-28 · Tai-Xiang Jiang, Michael K. Ng, Junjun Pan, Guangjing Song

The main aim of this paper is to develop a new algorithm for computing nonnegative low rank tensor approximation for nonnegative tensors that arise in many multi-dimensional imaging applications. Nonnegativity is one of …

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

2021-06-04 · ACL 2021 5 · Peiyu Liu, Ze-Feng Gao, Wayne Xin Zhao, Z. Y. Xie 외

This paper presents a novel pre-trained language models (PLM) compression approach based on the matrix product operator (short as MPO) from quantum many-body physics. It can decompose an original matrix into central tens…

Language ModelingLanguage ModellingModel Compression

Fast Learnings of Coupled Nonnegative Tensor Decomposition Using Optimal Gradient and Low-rank Approximation

2023-02-10 · XiuLin Wang, Jing Liu, FengYu Cong

Tensor decomposition is a fundamental technique widely applied in signal processing, machine learning, and various other fields. However, traditional tensor decomposition methods encounter limitations when jointly analyz…

EEGTensor Decomposition