Uplink Communication Efficient Differentially Private Sparse Optimization With Feature-Wise Distributed Data
Authors: Jian Lou, Yiu-ming Cheung
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | To obtain these guarantees, we provide a much generalized convergence analysis for block-coordinate Frank-Wolfe under arbitrary sampling, which greatly extends known convergence results that are only applicable to two specific block sampling distributions. We also design an active feature sharing scheme by utilizing private Johnson-Lindenstrauss transform, which is the key to updating local partial gradients in a differentially private and communication efficient manner. |
| Researcher Affiliation | Academia | Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong SAR, China {jianlou, ymc}@comp.hkbu.edu.hk |
| Pseudocode | Yes | Algorithm 1 Block-Coordinate Frank-Wolfe Algorithm With Arbitrary Sampling |
| Open Source Code | No | The paper does not provide any concrete access information (e.g., repository link, explicit statement of code release) for open-source code. |
| Open Datasets | No | The paper focuses on theoretical development and algorithm design for the LASSO problem and does not mention the use of any specific publicly available datasets for experimental training. |
| Dataset Splits | No | The paper focuses on theoretical development and algorithm design, and thus does not provide specific details on dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers needed to replicate any experiments. |
| Experiment Setup | No | The paper focuses on theoretical algorithm design and analysis, and therefore does not provide specific experimental setup details such as hyperparameter values or training configurations. |