Density Corrected Sparse Recovery when R.I.P. Condition Is Broken

Authors: Ming Lin, Zhengzhong Lan, Alexander G. Hauptmann

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove that when features exhibit cluster structures, which often happens in real applications, we are able to recover the sparse vector consistently. The consistency comes from our proposed density correction algorithm, which removes the variance of estimated cluster centers using cluster density. The proposed algorithm converges geometrically, achieves nearly optimal recovery bound O(s2 log(d)) where s is the sparsity and d is the nominal dimension.
Researcher Affiliation Academia Ming Lin, Zhengzhong Lan, Alexander G. Hauptmann Carnegie Mellon University Pittsburgh, PA, USA
Pseudocode Yes Algorithm 1 Density Corrected Sparse Recovery (DCSR)
Open Source Code No The paper does not provide any information or links regarding the availability of open-source code.
Open Datasets No The paper is theoretical and does not conduct experiments with specific datasets. It discusses 'training instances' in a general context, but no specific public dataset is mentioned or linked.
Dataset Splits No The paper is theoretical and does not include empirical experiments with validation dataset splits.
Hardware Specification No The paper is theoretical and does not mention any hardware specifications used for experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not provide details about an experimental setup, such as hyperparameters or training settings.