Generalized Dantzig Selector: Application to the k-support norm

Authors: Soumyadeep Chatterjee, Sheng Chen, Arindam Banerjee

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results confirm our theoretical analysis.
Researcher Affiliation Academia Soumyadeep Chatterjee Sheng Chen Arindam Banerjee Dept. of Computer Science & Engg. University of Minnesota, Twin Cities {chatter,shengc,banerjee}@cs.umn.edu
Pseudocode Yes Algorithm 1 ADMM for Generalized Dantzig Selector Algorithm 2 Algorithm for computing prox ICλ ( ) of sp
Open Source Code No The paper does not provide any explicit links to open-source code or state that code is released.
Open Datasets No The paper uses synthetic data generated internally: 'Data generation We fixed p = 600, and θ = (10, . . . , 10 I , 10, . . . , 10 I , 10, . . . , 10 I , 0, 0, . . ., 0 I throughout the experiment, in which nonzero entries were divided equally into three groups. The design matrix X were generated from a normal distribution such that the entries in the same group have the same mean sampled from N(0, 1). X was normalized afterwards. The response vector y was given by y = Xθ + 0.01 N(0, 1).'
Dataset Splits No The paper describes synthetic data generation and varying sample sizes ('n') for experiments, but it does not specify explicit training, validation, or test dataset splits, nor does it mention cross-validation.
Hardware Specification No The paper does not provide specific details about the hardware used for experiments.
Software Dependencies No The paper states: 'All experiments are implemented in MATLAB.' However, it does not specify a version number for MATLAB or any other software dependencies with their versions.
Experiment Setup Yes Data generation We fixed p = 600, and θ = (10, . . . , 10 I , 10, . . . , 10 I , 10, . . . , 10 I , 0, 0, . . ., 0 I throughout the experiment, in which nonzero entries were divided equally into three groups. The design matrix X were generated from a normal distribution such that the entries in the same group have the same mean sampled from N(0, 1). X was normalized afterwards. The response vector y was given by y = Xθ + 0.01 N(0, 1). We fixed n = 400 to obtain the ROC plot for k = {1, 10, 50}. λp ranged from 10 2 to 103. For each k, we repeated the experiment 100 times.