Discrete distribution estimation under user-level local differential privacy
We study discrete distribution estimation under user-level local differential privacy (LDP). In
user-level $\varepsilon $-LDP, each user has a $ m\ge1 $ samples and the privacy of all $ m …
user-level $\varepsilon $-LDP, each user has a $ m\ge1 $ samples and the privacy of all $ m …
Correlated quantization for distributed mean estimation and optimization
We study the problem of distributed mean estimation and optimization under communication
constraints. We propose a correlated quantization protocol whose error guarantee depends …
constraints. We propose a correlated quantization protocol whose error guarantee depends …
Robust gray codes approaching the optimal rate
Robust Gray codes were introduced by (Lolck and Pagh, SODA 2024). Informally, a robust
Gray code is a (binary) Gray code G so that, given a noisy version of the encoding G (j) of an …
Gray code is a (binary) Gray code G so that, given a noisy version of the encoding G (j) of an …
Shannon meets gray: Noise-robust, low-sensitivity codes with applications in differential privacy
Integer data is typically made differentially private by adding noise from a Discrete Laplace
(or Discrete Gaussian) distribution. We study the setting where differential privacy of a …
(or Discrete Gaussian) distribution. We study the setting where differential privacy of a …
Non-stochastic CDF estimation using threshold queries
Estimating the empirical distribution of a scalar-valued data set is a basic and fundamental
task. In this paper, we tackle the problem of estimating an empirical distribution in a setting …
task. In this paper, we tackle the problem of estimating an empirical distribution in a setting …
An information-theoretic method for collaborative distributed learning with limited communication
In this paper, we study the information transmission problem under the distributed learning
framework, where each worker node is merely permitted to transmit a m-dimensional statistic …
framework, where each worker node is merely permitted to transmit a m-dimensional statistic …
Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
L Vuursteen - arXiv preprint arXiv:2411.01275, 2024 - arxiv.org
We study distributed goodness-of-fit testing for discrete distribution under bandwidth and
differential privacy constraints. Information constraint distributed goodness-of-fit testing is a …
differential privacy constraints. Information constraint distributed goodness-of-fit testing is a …
Improved Construction of Robust Gray Code
D Fathollahi, M Wootters - arXiv preprint arXiv:2401.15291, 2024 - arxiv.org
A robust Gray code, formally introduced by (Lolck and Pagh, SODA 2024), is a Gray code
that additionally has the property that, given a noisy version of the encoding of an integer $ j …
that additionally has the property that, given a noisy version of the encoding of an integer $ j …
Adaptive Refinement Protocols for Distributed Distribution Estimation under -Losses
D Yuan, T Guo, Z Huang - arXiv preprint arXiv:2410.06884, 2024 - arxiv.org
Consider the communication-constrained estimation of discrete distributions under $\ell^ p $
losses, where each distributed terminal holds multiple independent samples and uses …
losses, where each distributed terminal holds multiple independent samples and uses …
Statistical Inference Under Information Constraints
Z Sun - 2022 - search.proquest.com
Data from user devices form the backbone of modern learning systems. Due to the
distributed nature of the devices and the enormous size of the data, the access to the data is …
distributed nature of the devices and the enormous size of the data, the access to the data is …