Connections Between Nuclear Norm and Frobenius Norm Based Representations

Abstract

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.

IEEE Trans. on Neural Networks and Learning Systems, 2016

Cited by in corpus (10)

• Robust Graph Learning from Noisy Data
• Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework
• Fast Robust PCA on Graphs
• Deep Dictionary Learning: A PARametric NETwork Approach
• A Sparse Model-inspired Deep Thresholding Network for Exponential Signal Reconstruction -- Application in Fast Biological Spectroscopy
• Multi Resolution Analysis (MRA) for Approximate Self-Attention
• Kernel Truncated Regression Representation for Robust Subspace Clustering
• Privacy-preserving Channel Estimation in Cell-free Hybrid Massive MIMO Systems
• Deep Double Sparsity Encoder: Learning to Sparsify Not Only Features But Also Parameters
• Deep Latent Factor Model for Collaborative Filtering