Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization
Authors: Meisam Razaviyayn, Mingyi Hong, Zhi-Quan Luo, Jong-Shi Pang
NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The numerical experiments suggest that for a special case of Lasso minimization problem, the cyclic block selection rule can outperform the randomized rule. |
| Researcher Affiliation | Academia | Electrical Engineering Department, Stanford University Industrial and Manufacturing Systems Engineering, Iowa State University Department of Electrical and Computer Engineering, University of Minnesota Department of Industrial and Systems Engineering, University of Southern California |
| Pseudocode | Yes | Algorithm 1 Parallel Successive Convex Approximation (PSCA) Algorithm |
| Open Source Code | No | The paper does not provide any explicit statements or links indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper defines how matrix A is generated ('according to the Nesterov s approach [5]') but does not provide access information (link, DOI, citation with author/year) for a specific public dataset used for training the Lasso problem. |
| Dataset Splits | No | The paper does not provide specific details on dataset splits (e.g., percentages, sample counts, or predefined splits with citations) for training, validation, or testing. |
| Hardware Specification | No | The paper mentions 'multi-core computing platforms' and 'number of processors' (q=4, 8, 16, 32) but does not provide specific details about the hardware used (e.g., CPU/GPU models, memory). |
| Software Dependencies | No | The paper does not specify any software names with version numbers that would be necessary to replicate the experiments. |
| Experiment Setup | No | The paper mentions 'constant step-size γ and proximal coefficient α' and 'block size is set to one', but it does not provide the specific numerical values of these hyperparameters (γ and α) used for the experiments shown in the figures. |