paper-with-me

홈 › Papers

Connections Between Nuclear Norm and Frobenius Norm Based Representations

2015-02-26 · Xi Peng, Can-Yi Lu, Zhang Yi, Huajin Tang

A lot of works have shown that frobenius-norm based representation (FNR) is competitive to sparse representation and nuclear-norm based representation (NNR) in numerous tasks such as subspace clustering. Despite the success of FNR in experimental studies, less theoretical analysis is provided to understand its working mechanism. In this paper, we fill this gap by building the theoretical connections between FNR and NNR. More specially, we prove that: 1) when the dictionary can provide enough representative capacity, FNR is exactly NNR even though the data set contains the Gaussian noise, Laplacian noise, or sample-specified corruption, 2) otherwise, FNR and NNR are two solutions on the column space of the dictionary.

📄 PDF Abstract BibTeX arXiv:1502.07423

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Similar Papers 제목 키워드 기반

Quaternion Nuclear Norm minus Frobenius Norm Minimization for color image reconstruction

2024-09-12 · Yu Guo, Guoqing Chen, Tieyong Zeng, Qiyu Jin 외

Color image restoration methods typically represent images as vectors in Euclidean space or combinations of three monochrome channels. However, they often overlook the correlation between these channels, leading to color…

DeblurringDenoisingImage ReconstructionImage Restoration

On the regularization landscape for the linear recommendation models

2021-09-29 · Dong Li, Zhenming Liu, Ruoming Jin, Zhi Liu 외

Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders several standard recommendation benchmarks. While these algorithms were built on different …

Low Rank Matrix Completion with Exponential Family Noise

2015-02-24 · Jean Lafond

The matrix completion problem consists in reconstructing a matrix from a sample of entries, possibly observed with noise. A popular class of estimator, known as nuclear norm penalized estimators, are based on minimizing …

Low-Rank Matrix CompletionMatrix CompletionPrediction

Nuclear Norm Regularization for Deep Learning

2024-05-23 · Christopher Scarvelis, Justin Solomon

Penalizing the nuclear norm of a function's Jacobian encourages it to locally behave like a low-rank linear map. Such functions vary locally along only a handful of directions, making the Jacobian nuclear norm a natural …

Deep LearningDenoisingRepresentation Learning

Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations

2020-03-27 · CVPR 2020 6 · Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li 외

The learning of the deep networks largely relies on the data with human-annotated labels. In some label insufficient situations, the performance degrades on the decision boundary with high data density. A common solution…

DiversityDomain Adaptation