Private Stochastic Convex Optimization and Sparse Learning with Heavy-tailed Data Revisited

Authors: Youming Tao, Yulian Wu, Xiuzhen Cheng, Di Wang

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DPSCO) with heavy-tailed data... We propose a novel robust and private mean estimator which is optimal. Based on its idea, we then extend to the general d-dimensional space and study DP-SCO... We also provide lower bounds... We propose a new method and show it is also optimal...
Researcher Affiliation Academia Youming Tao1 , Yulian Wu2 , Xiuzhen Cheng1 and Di Wang2 1School of Computer Science, Shandong University 2CEMSE, KAUST di.wang@kaust.edu.sa
Pseudocode Yes Algorithm 1 Truncation Based DP Mean Estimator: DPODME Tϵ,δ,ξ(X)
Open Source Code No The paper does not include any explicit statement about releasing source code for the described methodology, nor does it provide any links to a code repository.
Open Datasets No The paper is theoretical and does not mention specific datasets or their public availability for training purposes. It refers to "data samples X" without specifying a publicly accessible dataset source or name.
Dataset Splits No The paper is theoretical and does not conduct experiments, therefore it does not provide specific dataset split information for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe experiments, thus no specific hardware details used for running experiments are mentioned.
Software Dependencies No The paper is theoretical and does not describe experiments, thus no specific ancillary software details with version numbers are provided.
Experiment Setup No The paper is theoretical and focuses on algorithm design and proofs, therefore it does not provide specific experimental setup details, hyperparameters, or training configurations.