arXiv subjects

Ruyu Zhou

Publications and source records attributed to Ruyu Zhou.

4 recordsLinked to original sources

arXiv2025

PRECISE: PRivacy-loss-Efficient and Consistent Inference based on poSterior quantilEs

Differential Privacy (DP) is a mathematical framework for releasing information with formal privacy guarantees. While numerous DP procedures have been developed for statistical analysis and machine learning, valid statistical inference methods offering high utility under DP constraints remain limited. We formalize this gap by introducing the notion of valid Privacy-Preserving Interval Estimation (PPIE) and propose a new PPIE approach -- PRECISE -- to constructing privacy-preserving posterior intervals with the goal of offering a better privacy-utility tradeoff than existing DP inferential methods. PRECISE is a general-purpose and model-agnostic method that generates intervals using quantile estimates obtained from a sanitized posterior histogram with DP guarantees. We explicitly characterize the global sensitivity of the histogram formed from posterior samples for the parameter of interest, enabling its sanitization with formal DP guarantees. We also analyze the sources of error in the mean squared error (MSE) of the histogram-based private quantile estimator and prove its consistency for the true posterior quantiles as the sample size or privacy loss increases with along with its rate of convergence. We conduct extensive experiments to compare the utilities of PRECISE with common existing privacy-preserving inferential approaches across a wide range of inferential tasks, data types and sizes, DP types, and privacy loss levels. The results demonstrated a significant advantage of PRECISE with its nominal coverage and substantially narrower intervals than the existing methods, which are prone to either under-coverage or impractically wide intervals.

stat.ME↗

arXiv2025

Efficient approximation of Earth Mover's Distance Based on Nearest Neighbor Search

Earth Mover's Distance (EMD) is an important similarity measure between two distributions, used in computer vision and many other application domains. However, its exact calculation is computationally and memory intensive, which hinders its scalability and applicability for large-scale problems. Various approximate EMD algorithms have been proposed to reduce computational costs, but they suffer lower accuracy and may require additional memory usage or manual parameter tuning. In this paper, we present a novel approach, NNS-EMD, to approximate EMD using Nearest Neighbor Search (NNS), in order to achieve high accuracy, low time complexity, and high memory efficiency. The NNS operation reduces the number of data points compared in each NNS iteration and offers opportunities for parallel processing. We further accelerate NNS-EMD via vectorization on GPU, which is especially beneficial for large datasets. We compare NNS-EMD with both the exact EMD and state-of-the-art approximate EMD algorithms on image classification and retrieval tasks. We also apply NNS-EMD to calculate transport mapping and realize color transfer between images. NNS-EMD can be 44x to 135x faster than the exact EMD implementation, and achieves superior accuracy, speedup, and memory efficiency over existing approximate EMD methods.

cs.CV↗

arXiv2024

Enhancing Trade-offs in Privacy, Utility, and Computational Efficiency through MUltistage Sampling Technique (MUST)

Applying a randomized algorithm to a subset rather than the entire dataset amplifies privacy guarantees. We propose a class of subsampling methods ``MUltistage Sampling Technique (MUST)'' for privacy amplification (PA) in the context of differential privacy (DP). We conduct comprehensive analyses of the PA effects and utility for several 2-stage MUST procedures through newly introduced concept including strong vs weak PA effects and aligned privacy profile. We provide the privacy loss composition analysis over repeated applications of MUST via the Fourier accountant algorithm. Our theoretical and empirical results suggest that MUST offers stronger PA in $ε$ than the common one-stage sampling procedures including Poisson sampling, sampling without replacement, and sampling with replacement, while the results on $δ$ vary case by case. Our experiments show that MUST is non-inferior in the utility and stability of privacy-preserving (PP) outputs to one-stage subsampling methods at similar privacy loss while enhancing the computational efficiency of algorithms that require complex function calculations on distinct data points. MUST can be seamlessly integrated into stochastic optimization algorithms or procedures that involve parallel or simultaneous subsampling when DP guarantees are necessary.

stat.ML↗

arXiv2023

Privacy-preserving Inference of Group Mean Difference in Zero-inflated Right Skewed Data with Partitioning and Censoring

We examine privacy-preserving inferences of group mean differences in zero-inflated right-skewed (zirs) data. Zero inflation and right skewness are typical characteristics of ads clicks and purchases data collected from e-commerce and social media platforms, where we also want to preserve user privacy to ensure that individual data is protected. In this work, we develop likelihood-based and model-free approaches to analyzing zirs data with formal privacy guarantees. We first apply partitioning and censoring (PAC) to ``regularize'' zirs data to get the PAC data. We expect inferences based on PAC to have better inferential properties and more robust privacy considerations compared to analyzing the raw data directly. We conduct theoretical analysis to establish the MSE consistency of the privacy-preserving estimators from the proposed approaches based on the PAC data and examine the rate of convergence in the number of partitions and privacy loss parameters. The theoretical results also suggest that it is the sampling error of PAC data rather than the sanitization error that is the limiting factor in the convergence rate. We conduct extensive simulation studies to compare the inferential utility of the proposed approach for different types of zirs data, sample size and partition size combinations, censoring scenarios, mean differences, privacy budgets, and privacy loss composition schemes. We also apply the methods to obtain privacy-preserving inference for the group mean difference in a real digital ads click-through data set. Based on the theoretical and empirical results, we make recommendations regarding the usage of these methods in practice.

stat.ME↗