paper-with-me

Papers

Notes on Sampled Gaussian Mechanism

2024-09-06 · Nikita P. Kalinin

In these notes, we prove a recent conjecture posed in the paper by R\"ais\"a, O. et al. [Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimization (2024)]. Theorem 6.2 of the paper asserts that for the Sampled Gaussian Mechanism - a composition of subsampling and additive Gaussian noise, the effective noise level, $\sigma_{\text{eff}} = \frac{\sigma(q)}{q}$, decreases as a function of the subsampling rate $q$. Consequently, larger subsampling rates are preferred for better privacy-utility trade-offs. Our notes provide a rigorous proof of Conjecture 6.3, which was left unresolved in the original paper, thereby completing the proof of Theorem 6.2.

📄 PDF Abstract BibTeX arXiv:2409.04636

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Rényi Differential Privacy of the Sampled Gaussian Mechanism

2019-08-28 · Ilya Mironov, Kunal Talwar, Li Zhang

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications. The mechanism's unexpected power is derived f…

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

2020-06-12 · Antti Koskela, Joonas Jälkö, Lukas Prediger, Antti Honkela

We propose a numerical accountant for evaluating the tight $(\varepsilon,\delta)$-privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy loss distribution formalism and it us…

Subsampled Rényi Differential Privacy and Analytical Moments Accountant

2018-07-31 · Yu-Xiang Wang, Borja Balle, Shiva Kasiviswanathan

We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms. Specifically, we provide a tight upper bound…

BIG-bench Machine Learning

Shuffle Gaussian Mechanism for Differential Privacy

2022-06-20 · Seng Pei Liew, Tsubasa Takahashi

We study Gaussian mechanism in the shuffle model of differential privacy (DP). Particularly, we characterize the mechanism's R\'enyi differential privacy (RDP), showing that it is of the form: $$ \epsilon(\lambda) \leq \…

Federated Learning

Efficient Standardization of Clinical Notes using Large Language Models

2024-12-31 · Daniel B. Hier, Michael D. Carrithers, Thanh Son Do, Tayo Obafemi-Ajayi

Clinician notes are a rich source of patient information but often contain inconsistencies due to varied writing styles, colloquialisms, abbreviations, medical jargon, grammatical errors, and non-standard formatting. The…

Language ModelingLanguage ModellingLarge Language Model