SVD-free Convex-Concave Approaches for Nuclear Norm Regularization
Authors: Yichi Xiao, Zhe Li, Tianbao Yang, Lijun Zhang
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present numerical experiments on real datasets to demonstrate the efficiency of the proposed algorithms, and more results can be found in the supplementary. |
| Researcher Affiliation | Academia | Yichi Xiao1 , Zhe Li2 , Tianbao Yang2, Lijun Zhang1 1National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China 2Department of Computer Science, the University of Iowa, Iowa City, IA 52242, USA |
| Pseudocode | Yes | Algorithm 1 SVD-fre E CONvex-Concav E Algorithm (SECONE) |
| Open Source Code | No | The paper does not provide any explicit statement or link regarding the public availability of its source code. |
| Open Datasets | Yes | We use the News202 dataset, which contains m = 11, 269 instances, each of which has n = 20, 302 features (we filter the features which appear less than 7 times). http://qwone.com/ jason/20Newsgroups/ |
| Dataset Splits | No | The paper uses datasets like News202 and Facebook100, and mentions details like 'We flip 15% of randomly chosen entries' for link prediction, but it does not provide specific train/validation/test dataset splits (e.g., percentages or sample counts) nor does it mention cross-validation. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU models, CPU models, or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper does not provide any specific ancillary software details, such as library names with version numbers, needed to replicate the experiments. |
| Experiment Setup | Yes | According to Theorem 1, we set step sizes in Algorithm 1 as ηt = c1/t and τt = c2/t, where c1, c2 are some constants. The same step size ηt = c1/t is also used for GD and PGD. We tune the value of c1 and c2 in a range of {1e-5, 1e-4, . . . , 1e10} and report the best results based on the objective value. |