English
Related papers

Related papers: Trade-off Functions for DP-SGD with Subsampling ba…

200 papers

Synchronous mini-batch SGD is state-of-the-art for large-scale distributed machine learning. However, in practice, its convergence is bottlenecked by slow communication rounds between worker nodes. A natural solution to reduce communication…

Machine Learning · Computer Science 2019-04-26 Kumar Kshitij Patel , Aymeric Dieuleveut

The standard closed form lower bound on $\sigma$ for providing $(\epsilon, \delta)$-differential privacy by adding zero mean Gaussian noise with variance $\sigma^2$ is $\sigma > \Delta\sqrt {2}(\epsilon^{-1}) \sqrt {\log \left(…

Cryptography and Security · Computer Science 2021-01-22 Staal A. Vinterbo

The shuffle model of Differential Privacy (DP) has gained significant attention in privacy-preserving data analysis due to its remarkable tradeoff between privacy and utility. It is characterized by adding a shuffling procedure after each…

Combinatorics · Mathematics 2024-01-10 E Chen , Yang Cao , Yifei Ge

Many algorithms have been developed to estimate probability distributions subject to differential privacy (DP): such an algorithm takes as input independent samples from a distribution and estimates the density function in a way that is…

Cryptography and Security · Computer Science 2024-12-17 Albert Cheu , Debanuj Nayak

Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the…

Machine Learning · Computer Science 2021-07-06 Alain Rakotomamonjy , Liva Ralaivola

Auditing Differentially Private Stochastic Gradient Descent (DP-SGD) in the final model setting is challenging and often results in empirical lower bounds that are significantly looser than theoretical privacy guarantees. We introduce a…

Cryptography and Security · Computer Science 2025-02-25 Sangyeon Yoon , Wonje Jeung , Albert No

In inference problems involving a multi-dimensional parameter $\theta$, it is often natural to consider decision rules that have a risk which is invariant under some group $G$ of permutations of $\theta$. We show that this implies that the…

Methodology · Statistics 2014-07-01 Erik van Zwet

ldp deployments are vulnerable to inference attacks as an adversary can link the noisy responses to their identity and subsequently, auxiliary information using the order of the data. An alternative model, shuffle DP, prevents this by…

Machine Learning · Computer Science 2021-10-18 Casey Meehan , Amrita Roy Chowdhury , Kamalika Chaudhuri , Somesh Jha

Differential privacy (DP) is becoming increasingly important for deployed machine learning applications because it provides strong guarantees for protecting the privacy of individuals whose data is used to train models. However, DP…

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient…

Machine Learning · Computer Science 2025-07-31 Afshin Khadangi , Amir Sartipi , Igor Tchappi , Ramin Bahmani , Gilbert Fridgen

An oblivious subspace embedding (OSE), characterized by parameters $m,n,d,\epsilon,\delta$, is a random matrix $\Pi\in \mathbb{R}^{m\times n}$ such that for any $d$-dimensional subspace $T\subseteq \mathbb{R}^n$, $\Pr_\Pi[\forall x\in T,…

Data Structures and Algorithms · Computer Science 2023-07-14 Yi Li , Mingmou Liu

Differential privacy (DP) considers a scenario, where an adversary has almost complete information about the entries of a database This worst-case assumption is likely to overestimate the privacy thread for an individual in real life.…

Cryptography and Security · Computer Science 2025-04-16 Dennis Breutigam , Rüdiger Reischuk

We consider the privacy amplification properties of a sampling scheme in which a user's data is used in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps. This sampling scheme has been recently applied in the…

Machine Learning · Computer Science 2026-02-20 Vitaly Feldman , Moshe Shenfeld

We study how the batch size affects the total gradient variance in differentially private stochastic gradient descent (DP-SGD), seeking a theoretical explanation for the usefulness of large batch sizes. As DP-SGD is the basis of modern DP…

Machine Learning · Statistics 2024-09-20 Ossi Räisä , Joonas Jälkö , Antti Honkela

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our…

Machine Learning · Computer Science 2020-04-01 Shipra Agrawal , Randy Jia

In differentially private (DP) machine learning, the privacy guarantees of DP mechanisms are often reported and compared on the basis of a single $(\varepsilon, \delta)$-pair. This practice overlooks that DP guarantees can vary…

Cryptography and Security · Computer Science 2025-05-06 Georgios Kaissis , Stefan Kolek , Borja Balle , Jamie Hayes , Daniel Rueckert

We aim to provide a unified convergence analysis for permutation-based Stochastic Gradient Descent (SGD), where data examples are permuted before each epoch. By examining the relations among permutations, we categorize existing…

Machine Learning · Computer Science 2025-01-28 Yipeng Li , Xinchen Lyu , Zhenyu Liu

Stochastic Gradient Descent (SGD) is an important algorithm in machine learning. With constant learning rates, it is a stochastic process that, after an initial phase of convergence, generates samples from a stationary distribution. We show…

Machine Learning · Statistics 2017-09-12 Stephan Mandt , Matthew D. Hoffman , David M. Blei

The lower the distortion of an estimator, the more the distribution of its outputs generally deviates from the distribution of the signals it attempts to estimate. This phenomenon, known as the perception-distortion tradeoff, has captured…

Image and Video Processing · Electrical Eng. & Systems 2021-07-07 Dror Freirich , Tomer Michaeli , Ron Meir

Stochastic gradient descent (SGD) is a prevalent optimization technique for large-scale distributed machine learning. While SGD computation can be efficiently divided between multiple machines, communication typically becomes a bottleneck…

Machine Learning · Computer Science 2021-05-24 Dmitrii Avdiukhin , Grigory Yaroslavtsev