paper-with-me

Papers

Learning Parameter Sharing with Tensor Decompositions and Sparsity

2024-11-14 · Cem Üyük, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou

Large neural networks achieve remarkable performance, but their size hinders deployment on resource-constrained devices. While various compression techniques exist, parameter sharing remains relatively unexplored. This paper introduces Fine-grained Parameter Sharing (FiPS), a novel algorithm that leverages the relationship between parameter sharing, tensor decomposition, and sparsity to efficiently compress large vision transformer models. FiPS employs a shared base and sparse factors to represent shared neurons across multi-layer perception (MLP) modules. Shared parameterization is initialized via Singular Value Decomposition (SVD) and optimized by minimizing block-wise reconstruction error. Experiments demonstrate that FiPS compresses DeiT-B and Swin-L MLPs to 25-40% of their original parameter count while maintaining accuracy within 1 percentage point of the original models.

📄 PDF Abstract BibTeX arXiv:2411.09816

Code (1)

cemuyuk/FiPS pytorch

Tasks

Tensor Decomposition

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

A tensor network formalism for neuro-symbolic AI

2026-01-21 · Alex Goessmann, Janina Schütte, Maximilian Fröhlich, Martin Eigel arxiv

The unification of neural and symbolic approaches to artificial intelligence remains a central open challenge. In this work, we introduce a tensor network formalism, which captures sparsity principles originating in the …

Identifiability of Nonnegative Tucker Decompositions -- Part I: Theory

2025-05-19 · Subhayan Saha, Giovanni Barbarino, Nicolas Gillis

Tensor decompositions have become a central tool in data science, with applications in areas such as data analysis, signal processing, and machine learning. A key property of many tensor decompositions, such as the canon…

Tensor Decomposition

Tensor Decompositions in Deep Learning

2020-02-26 · Davide Bacciu, Danilo P. Mandic

The paper surveys the topic of tensor decompositions in modern machine learning applications. It focuses on three active research topics of significant relevance for the community. After a brief review of consolidated wo…

BIG-bench Machine LearningDeep Learning

Deep convolutional neural network compression via coupled tensor decomposition

2020-11-16 · IEEE Journal of Selected Topics in Signal Processing 2020 11 · Weize Sun, Shaowu Chen, Lei Huang, Hing Cheung So 외

Large neural networks have aroused impressive progress in various real world applications. However, the expensive storage and computational resources requirement for running deep networks make them problematic to be depl…

Image ReconstructionNeural Network CompressionTensor Decomposition

Polynomial-time Tensor Decompositions with Sum-of-Squares

2016-10-06 · Tengyu Ma, Jonathan Shi, David Steurer

We give new algorithms based on the sum-of-squares method for tensor decomposition. Our results improve the best known running times from quasi-polynomial to polynomial for several problems, including decomposing random …

Tensor Decomposition