Subset Selection under Noise
Authors: Chao Qian, Jing-Cheng Shi, Yang Yu, Ke Tang, Zhi-Hua Zhou
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The empirical results on influence maximization and sparse regression problems show the superior performance of PONSS. We have conducted experiments on influence maximization and sparse regression problems, two typical subset selection applications with the objective function being submodular and non-submodular, respectively. The results on real-world data sets show that POSS is better than the greedy algorithm in most cases, and PONSS clearly outperforms POSS and the greedy algorithm. |
| Researcher Affiliation | Academia | 1Anhui Province Key Lab of Big Data Analysis and Application, USTC, China 2National Key Lab for Novel Software Technology, Nanjing University, China 3Shenzhen Key Lab of Computational Intelligence, SUSTech, China |
| Pseudocode | Yes | Algorithm 1 Greedy Algorithm; Algorithm 2 POSS Algorithm; Algorithm 3 PONSS Algorithm |
| Open Source Code | No | The paper does not provide an explicit statement or a link indicating the release of the source code for the methodology described. |
| Open Datasets | Yes | We use two real-world data sets: ego-Facebook and Weibo. ego-Facebook is downloaded from http: //snap.stanford.edu/data/index.html, and Weibo is crawled from a Chinese microblogging site Weibo.com like Twitter. We use two data sets from http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/ datasets/. |
| Dataset Splits | No | The paper mentions using a random sample of instances for estimation and averaging over simulations, but it does not specify explicit training, validation, or test dataset splits (e.g., percentages or counts) typically used for reproducibility. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory, or cloud instances) used for running the experiments. |
| Software Dependencies | No | The paper does not specify any software dependencies or library versions used for the experiments. |
| Experiment Setup | Yes | The number T of iterations in POSS is set to 2ek2n as suggested by Theorem 3. For PONSS, B is set to k, and θ is set to 1, which is obviously not smaller than ϵ. |