Analysis of Robust PCA via Local Incoherence

2015-12-01 · NeurIPS 2015 12 · Huishuai Zhang, Yi Zhou, Yingbin Liang

We investigate the robust PCA problem of decomposing an observed matrix into the sum of a low-rank and a sparse error matrices via convex programming Principal Component Pursuit (PCP). In contrast to previous studies that assume the support of the error matrix is generated by uniform Bernoulli sampling, we allow non-uniform sampling, i.e., entries of the low-rank matrix are corrupted by errors with unequal probabilities. We characterize conditions on error corruption of each individual entry based on the local incoherence of the low-rank matrix, under which correct matrix decomposition by PCP is guaranteed. Such a refined analysis of robust PCA captures how robust each entry of the low rank matrix combats error corruption. In order to deal with non-uniform error corruption, our technical proof introduces a new weighted norm and develops/exploits the concentration properties that such a norm satisfies.

📄 PDF Abstract BibTeX

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…

Model-free Nonconvex Matrix Completion: Local Minima Analysis and Applications in Memory-efficient Kernel PCA

2017-11-06 · Ji Chen, Xiao-Dong Li

This work studies low-rank approximation of a positive semidefinite matrix from partial entries via nonconvex optimization. We characterized how well local-minimum based low-rank factorization approximates a fixed positi…

Clustering Dimensionality Reduction Matrix Completion

Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume

2026-02-27 · Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low arxiv

Despite their capabilities, Multimodal Large Language Models (MLLMs) may produce plausible but erroneous outputs, hindering reliable deployment. Accurate uncertainty metrics could enable escalation of unreliable queries …

Audio Generation

Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification

2019-08-21 · Zhao Zhang, Yulin Sun, Zheng Zhang, Yang Wang 외

In this paper, we extend the popular dictionary pair learning (DPL) into the scenario of twin-projective latent flexible DPL under a structured twin-incoherence. Technically, a novel framework called Twin-Projective Late…

General Classification

CluHTM - Semantic Hierarchical Topic Modeling based on CluWords

2020-07-01 · ACL 2020 6 · Felipe Viegas, Washington Cunha, Christian Gomes, Ant{\^o}nio Pereira 외

Hierarchical Topic modeling (HTM) exploits latent topics and relationships among them as a powerful tool for data analysis and exploration. Despite advantages over traditional topic modeling, HTM poses its own challenges…

QuIP: 2-Bit Quantization of Large Language Models With Guarantees

2023-07-25 · NeurIPS 2023 11 · Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Christopher De Sa

This work studies post-training parameter quantization in large language models (LLMs). We introduce quantization with incoherence processing (QuIP), a new method based on the insight that quantization benefits from $\te…

Quantization