paper-with-me

홈 › Papers

Sparse PCA on fixed-rank matrices

2022-01-07 · Alberto Del Pia

Sparse PCA is the optimization problem obtained from PCA by adding a sparsity constraint on the principal components. Sparse PCA is NP-hard and hard to approximate even in the single-component case. In this paper we settle the computational complexity of sparse PCA with respect to the rank of the covariance matrix. We show that, if the rank of the covariance matrix is a fixed value, then there is an algorithm that solves sparse PCA to global optimality, whose running time is polynomial in the number of features. We also prove a similar result for the version of sparse PCA which requires the principal components to have disjoint supports.

📄 PDF Abstract BibTeX arXiv:2201.02487

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

Similar Papers 제목 키워드 기반

Restricted Eigenvalue from Stable Rank with Applications to Sparse Linear Regression

2017-07-25 · Shiva Prasad Kasiviswanathan, Mark Rudelson

High-dimensional settings, where the data dimension ($d$) far exceeds the number of observations ($n$), are common in many statistical and machine learning applications. Methods based on $\ell_1$-relaxation, such as Lass…

regression

Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models

2021-11-30 · ICLR 2022 4 · Tri Dao, Beidi Chen, Kaizhao Liang, Jiaming Yang 외

Overparameterized neural networks generalize well but are expensive to train. Ideally, one would like to reduce their computational cost while retaining their generalization benefits. Sparse model training is a simple an…

Language ModelingLanguage Modelling

SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining

2024-06-04 · Andi Han, Jiaxiang Li, Wei Huang, Mingyi Hong 외

Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explor…

QuantizationSparse Learning

Generalization Bounds for Rank-sparse Neural Networks

2025-10-24 · Antoine Ledent, Rodrigo Alves, Yunwen Lei arxiv

It has been recently observed in much of the literature that neural networks exhibit a bottleneck rank property: for larger depths, the activation and weights of neural networks trained with gradient-based methods tend t…

Fixed-rank matrix factorizations and Riemannian low-rank optimization

2012-09-03 · B. Mishra, G. Meyer, S. Bonnabel, R. Sepulchre

Motivated by the problem of learning a linear regression model whose parameter is a large fixed-rank non-symmetric matrix, we consider the optimization of a smooth cost function defined on the set of fixed-rank matrices.…

Low-Rank Matrix CompletionMatrix Completion