paper-with-me

Papers

Oblivious subspace embeddings for compressed Tucker decompositions

2024-06-13 · Matthew Pietrosanu, Bei Jiang, Linglong Kong

Emphasis in the tensor literature on random embeddings (tools for low-distortion dimension reduction) for the canonical polyadic (CP) tensor decomposition has left analogous results for the more expressive Tucker decomposition comparatively lacking. This work establishes general Johnson-Lindenstrauss (JL) type guarantees for the estimation of Tucker decompositions when an oblivious random embedding is applied along each mode. When these embeddings are drawn from a JL-optimal family, the decomposition can be estimated within $\varepsilon$ relative error under restrictions on the embedding dimension that are in line with recent CP results. We implement a higher-order orthogonal iteration (HOOI) decomposition algorithm with random embeddings to demonstrate the practical benefits of this approach and its potential to improve the accessibility of otherwise prohibitive tensor analyses. On moderately large face image and fMRI neuroimaging datasets, empirical results show that substantial dimension reduction is possible with minimal increase in reconstruction error relative to traditional HOOI ($\leq$5% larger error, 50%-60% lower computation time for large models with 50% dimension reduction along each mode). Especially for large tensors, our method outperforms traditional higher-order singular value decomposition (HOSVD) and recently proposed TensorSketch methods.

📄 PDF Abstract BibTeX arXiv:2406.09387

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality ReductionTensor Decomposition

Methods 이 논문이 사용한 방법론

TuckER TuckER

Similar Papers 제목 키워드 기반

Lower Memory Oblivious (Tensor) Subspace Embeddings with Fewer Random Bits: Modewise Methods for Least Squares

2019-12-17 · M. A. Iwen, D. Needell, E. Rebrova, A. Zare

In this paper new general modewise Johnson-Lindenstrauss (JL) subspace embeddings are proposed that are both considerably faster to generate and easier to store than traditional JL embeddings when working with extremely …

Near-Linear Time and Fixed-Parameter Tractable Algorithms for Tensor Decompositions

2022-07-15 · Arvind V. Mahankali, David P. Woodruff, Ziyu Zhang

We study low rank approximation of tensors, focusing on the tensor train and Tucker decompositions, as well as approximations with tree tensor networks and more general tensor networks. For tensor train decomposition, we…

Dimensionality ReductionTensor DecompositionTensor Networks

Optimal Oblivious Subspace Embeddings with Near-optimal Sparsity

2024-11-13 · Shabarish Chenakkod, Michał Dereziński, Xiaoyu Dong

An oblivious subspace embedding is a random $m\times n$ matrix $\Pi$ such that, for any $d$-dimensional subspace, with high probability $\Pi$ preserves the norms of all vectors in that subspace within a $1\pm\epsilon$ fa…

Rethinking Compressed Convolution Neural Network from a Statistical Perspective

2021-01-01 · Feiqing Huang, Yuefeng Si, Guodong Li

Many designs have recently been proposed to improve the model efficiency of convolutional neural networks (CNNs) at a fixed resource budget, while there is a lack of theoretical analysis to justify them. This paper first…

Tensor Decomposition

Subspace Embeddings for the Polynomial Kernel

2014-12-01 · NeurIPS 2014 12 · Haim Avron, Huy Nguyen, David Woodruff

Sketching is a powerful dimensionality reduction tool for accelerating statistical learning algorithms. However, its applicability has been limited to a certain extent since the crucial ingredient, the so-called obliviou…

Dimensionality Reduction