Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization

Authors: Bargav Jayaraman, Lingxiao Wang, David Evans, Quanquan Gu

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on real world data sets demonstrate that our methods provide substantial utility gains for typical privacy requirements.
Researcher Affiliation Academia Bargav Jayaraman Department of Computer Science University of Virginia Charlottesville, VA 22903 bj4nq@virginia.edu Lingxiao Wang Department of Computer Science University of California, Los Angeles Los Angeles, CA 90095 lingxw@cs.ucla.edu David Evans Department of Computer Science University of Virginia Charlottesville, VA 22903 evans@virginia.edu Quanquan Gu Department of Computer Science University of California, Los Angeles Los Angeles, CA 90095 qgu@cs.ucla.edu
Pseudocode No The paper describes methods textually but does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes Code: https://github.com/bargavj/distributedMachine Learning.git
Open Datasets Yes For classification, we use a regularized logistic regression model over the KDDCup99 [25] data set (additional experiments on the Adult [2] data set yield similar results, described in Appendix B.3). ... For regression, we train a ridge regression model over the KDDCup98 [40] data set...
Dataset Splits No We randomly sample 70,000 records and divide it into training set of 50,000 records and test set of 20,000 records. (Only training and test sets are explicitly mentioned, not a separate validation set split.)
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., 'Python 3.8', 'PyTorch 1.9').
Experiment Setup Yes For all the experiments, we set Lipschitz constant G = 1, learning rate η = 1, regularization coefficient λ = 0.001, privacy budget ϵ = 0.5, failure probability δ = 0.001 and total number of iterations T = 1, 500 for gradient descent.