Private Stochastic Non-convex Optimization with Improved Utility Rates

Authors: Qiuchen Zhang, Jing Ma, Jian Lou, Li Xiong

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiment results on both shallow and deep neural networks when respectively applied to simple and complex real datasets corroborate the theoretical results.
Researcher Affiliation Academia 1Emory University 2Xidian University {qiuchen.zhang, jing.ma, jian.lou, lxiong}@emory.edu, jlou@xidian.edu.cn
Pseudocode Yes Algorithm 1 DPage EM
Open Source Code No The paper mentions supplementary material for proofs and experiment details/results but does not explicitly state that source code for the methodology is provided.
Open Datasets Yes We conduct experiments on two real datasets: MNIST and CIFAR-10.
Dataset Splits No The paper mentions using MNIST and CIFAR-10 datasets but does not provide specific training/test/validation split percentages, sample counts, or a detailed splitting methodology.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions software like Tensorflow and Py Torch but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes By setting π in eq.(4), ηk = ( 1 2)kη0, T k = (2)k T 0, tk Mon = (2)kt0 Mon, where η0 max{ θ(1 ϱ)2 2β , 1} and η0((T 0 t0 Mon) + 1 2(1 ϱ)t0 Mon) = 1 c4θµ for some 0 < c4 < 2 (which gives η0(T 0 t0 Mon + t0 Mon 1 2(1 ϱ)) > 1 2θµ), in Algorithm 1