Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]
Adversarially Robust Distributed Count Tracking via Partial Differential Privacy
Authors: Zhongzheng Xiong, Xiaoyi Zhu, zengfeng Huang
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study the distributed tracking model... We provide an affirmative answer to this question by giving a robust algorithm with optimal communication. To address this, we extend the differential privacy framework by introducing "partial differential privacy" and proving a new generalization theorem. This theorem may have broader applications beyond robust count tracking, making it of independent interest. The contributions of this paper are summarized as follows: 1. We initiate the study of adversarially robust distributed tracking and propose the first robust counting tracking algorithm with near optimal communication. 2. To overcome the inherent challenges that arise from the distributed nature of the problem, we introduce a relaxed (and more general) version of differential privacy and prove a new generalization theorem for this notion. We believe that this new generalization theorem can be of independent interest and may have broader applications beyond count tracking. |
| Researcher Affiliation | Academia | Zhongzheng Xiong School of Data Science Fudan University EMAIL Xiaoyi Zhu School of Data Science Fudan University EMAIL Zengfeng Huang School of Data Science Fudan University EMAIL |
| Pseudocode | Yes | Algorithm 1: Site i for a round; Algorithm 2: Server |
| Open Source Code | No | The paper does not provide any link to open-source code or an explicit statement about its release. |
| Open Datasets | No | The paper is theoretical and does not conduct experiments on empirical datasets; thus, it does not mention public dataset availability with concrete access information. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical data splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental hardware specifications. |
| Software Dependencies | No | The paper is theoretical and does not mention specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup with hyperparameters or system-level training settings. |