Dimension-free Private Mean Estimation for Anisotropic Distributions
Authors: Yuval Dagan, Michael Jordan, Xuelin Yang, Lydia Zakynthinou, Nikita Zhivotovskiy
NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We present differentially private algorithms for high-dimensional mean estimation. We develop estimators that are appropriate for such signals our estimators are (ε, δ)-differentially private and have sample complexity that is dimension-independent for anisotropic subgaussian distributions. We show that this is the optimal sample complexity for this task up to logarithmic factors. The paper does not include experiments. |
| Researcher Affiliation | Academia | Yuval Dagan School of Computer Science Tel Aviv University ydagan@tauex.tau.ac.il Michael I. Jordan Department of EECS and Statistics University of California Berkeley michael_jordan@berkeley.edu Xuelin Yang Department of Statistics University of California Berkeley xuelin@berkeley.edu Lydia Zakynthinou Department of EECS University of California Berkeley lydiazak@berkeley.edu Nikita Zhivotovskiy Department of Statistics University of California Berkeley zhivotovskiy@berkeley.edu |
| Pseudocode | Yes | Algorithm 1 Private Re-scaled Averaging: Avg M,λ,ε,δ(X) |
| Open Source Code | No | The paper does not contain any statement about releasing source code or a link to a code repository. The NeurIPS checklist confirms "The paper does not include experiments requiring code." and "The paper does not release new assets." |
| Open Datasets | No | The paper is theoretical and does not conduct empirical studies with datasets. Therefore, it does not provide concrete access information for a publicly available or open dataset. |
| Dataset Splits | No | The paper is theoretical and does not describe empirical experiments with dataset splits. |
| Hardware Specification | No | The paper is theoretical and does not conduct experiments, therefore no hardware specifications are provided. The NeurIPS checklist confirms "The paper does not include experiments." |
| Software Dependencies | No | The paper is theoretical and does not conduct experiments, therefore no specific software dependencies with version numbers are listed. The NeurIPS checklist confirms "The paper does not include experiments." |
| Experiment Setup | No | The paper is theoretical and does not conduct experiments, therefore no specific experimental setup details, such as hyperparameters or training configurations, are provided. The NeurIPS checklist confirms "The paper does not include experiments." |