Towards a Lower Sample Complexity for Robust One-bit Compressed Sensing
Authors: Rongda Zhu, Quanquan Gu
ICML 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our theory is verified by extensive numerical experiments, which clearly illustrate the superiority of our algorithm for both approximate signal and support recovery in the noisy setting. |
| Researcher Affiliation | Academia | Rongda Zhu RZHU4@ILLINOIS.EDU Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA Quanquan Gu QG5W@VIRGINIA.EDU Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA 22904, USA |
| Pseudocode | Yes | Algorithm 1 Find maximizer of f(µ) when µ 1/2b |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the described methodology. |
| Open Datasets | No | The paper describes generating synthetic datasets but does not provide concrete access information (link, DOI, formal citation) for a publicly available or open dataset. |
| Dataset Splits | No | The paper mentions 'cross validation' but does not provide specific dataset split information (percentages, counts, or explicit standard splits) for reproducibility. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory, compute resources) used for running the experiments are mentioned in the paper. |
| Software Dependencies | No | The paper does not provide specific software dependency details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | For each recovery task, we will tune C and b by cross validation and select λ and τ according to Theorem 4.3 for strong signals and Theorem 4.5 for general signals. For each parameter setting, we present the average results of 100 trials of our method and four other methods: Passive, Convex, BIHT and BIHT-ℓ2. ... We choose the noisy setting in (Plan & Vershynin, 2013a) by flipping the signs of measurements with a probability of 0.1. |