Safe Subspace Screening for Nuclear Norm Regularized Least Squares Problems
Authors: Qiang Zhou, Qi Zhao
ICML 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we perform experiments on several synthetic and real data sets to evaluate the performance of the proposed SSS. |
| Researcher Affiliation | Academia | Qiang Zhou ZHOUQIANG@U.NUS.EDU Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583 Qi Zhao ELEQIZ@NUS.EDU.SG Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583 |
| Pseudocode | No | The paper describes the proposed method in detail but does not include a clearly labeled pseudocode or algorithm block. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | PIE Face Image Data Set This data set used in this experiment consist of 11554 gray face images from 68 people, which were captured under various poses, illumination conditions and expressions (Sim et al., 2003; Cai et al., 2007). MNIST Handwritten Digit Data Set This data set consists of 70, 000 grey images of scanned handwritten digits (Le Cun et al., 1998). |
| Dataset Splits | No | The paper describes how X and Y are formed for each dataset, but it does not provide specific train/validation/test dataset splits (e.g., percentages or counts) or a clear splitting methodology for reproducing model evaluation results. |
| Hardware Specification | Yes | All experiments are performed on a workstation with Intel(R) Core(TM) i7-4930K 3.40 GHz CPU and 64G RAM |
| Software Dependencies | No | The paper mentions using specific algorithms like APG and ADMM, but it does not provide specific version numbers for any software libraries, programming languages, or other dependencies used in the experiments. |
| Experiment Setup | Yes | On each data set, we run the solver without and with SSS to optimize Eq. (2) along a sequence of 100 values of λ equally spaced on the logarithmic scale of λ/λmax from 0.001 to 0.95. |