Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

Authors: Lijun Ding, Liwei Jiang, Yudong Chen, Qing Qu, Zhihui Zhu

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The entire paper is a theoretical work, presenting definitions, theorems, proofs, and an algorithm (Algorithm 1) for a mathematical problem. There are no sections discussing empirical studies, datasets, performance metrics, or experimental results. For example, "Theorem 3.1", "Definition 2.1", "Algorithm 1" are prevalent throughout the document.
Researcher Affiliation Academia Xiaowei Zhang, Hongwei Liu, Guohua Liu, Lei Yang, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China, 100876.
Pseudocode Yes Algorithm 1: Subgradient Method for R-ORMR
Open Source Code No The paper does not provide any statement or link regarding the public release of source code for the described methodology.
Open Datasets No This theoretical paper does not involve experiments with datasets, and thus provides no information regarding publicly available or open datasets.
Dataset Splits No This theoretical paper does not involve experiments with datasets, and thus provides no information regarding dataset splits.
Hardware Specification No The paper does not describe any experimental setup that would require hardware specifications.
Software Dependencies No The paper, being purely theoretical, does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is a theoretical work and does not detail an experimental setup with hyperparameters or system-level training settings.