English
Related papers

Related papers: Optimal Best Arm Identification under Differential…

200 papers

We consider a novel stochastic multi-armed bandit problem called {\em good arm identification} (GAI), where a good arm is defined as an arm with expected reward greater than or equal to a given threshold. GAI is a pure-exploration problem…

The rapid development of affordable and compact high-fidelity sensors (e.g., cameras and LIDAR) allows robots to construct detailed estimates of their states and environments. However, the availability of such rich sensor information…

Optimization and Control · Mathematics 2021-09-20 Vincent Pacelli , Anirudha Majumdar

We consider the decentralized exploration problem: a set of players collaborate to identify the best arm by asynchronously interacting with the same stochastic environment. The objective is to insure privacy in the best arm identification…

Machine Learning · Computer Science 2023-01-18 Raphaël Féraud , Réda Alami , Romain Laroche

Large organizations that collect data about populations (like the US Census Bureau) release summary statistics that are used by multiple stakeholders for resource allocation and policy making problems. These organizations are also legally…

Databases · Computer Science 2021-11-08 David Pujol , Yikai Wu , Brandon Fain , Ashwin Machanavajjhala

Individual privacy accounting enables bounding differential privacy (DP) loss individually for each participant involved in the analysis. This can be informative as often the individual privacy losses are considerably smaller than those…

Cryptography and Security · Computer Science 2023-08-25 Antti Koskela , Marlon Tobaben , Antti Honkela

Local differential privacy (LDP) is increasingly employed in privacy-preserving machine learning to protect user data before sharing it with an untrusted aggregator. Most LDP methods assume that users possess only a single data record,…

Machine Learning · Computer Science 2025-05-05 Behnoosh Zamanlooy , Mario Diaz , Shahab Asoodeh

This paper presents a comprehensive study on the problem of Best Arm Retention (BAR), which has recently found applications in streaming algorithms for multi-armed bandits. In the BAR problem, the goal is to retain $m$ arms with the best…

Machine Learning · Computer Science 2025-04-17 Houshuang Chen , Yuchen He , Chihao Zhang

Given a dataset of $n$ i.i.d. samples from an unknown distribution $P$, we consider the problem of generating a sample from a distribution that is close to $P$ in total variation distance, under the constraint of differential privacy (DP).…

Data Structures and Algorithms · Computer Science 2023-06-23 Badih Ghazi , Xiao Hu , Ravi Kumar , Pasin Manurangsi

Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data…

Cryptography and Security · Computer Science 2024-04-04 Fei Wei , Ergute Bao , Xiaokui Xiao , Yin Yang , Bolin Ding

We present an asymptotically optimal $(\epsilon,\delta)$ differentially private mechanism for answering multiple, adaptively asked, $\Delta$-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm has a…

Data Structures and Algorithms · Computer Science 2021-11-09 Yuval Dagan , Gil Kur

In this paper, we address the challenge of differential privacy in the context of graph cuts, specifically focusing on the multiway cut and the minimum $k$-cut. We introduce edge-differentially private algorithms that achieve nearly optimal…

Cryptography and Security · Computer Science 2024-12-04 Rishi Chandra , Michael Dinitz , Chenglin Fan , Zongrui Zou

We study person-level differentially private (DP) mean estimation in the case where each person holds multiple samples. DP here requires the usual notion of distributional stability when $\textit{all}$ of a person's datapoints can be…

Data Structures and Algorithms · Computer Science 2024-07-22 Sushant Agarwal , Gautam Kamath , Mahbod Majid , Argyris Mouzakis , Rose Silver , Jonathan Ullman

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they…

We present new methods for assessing the privacy guarantees of an algorithm with regard to R\'enyi Differential Privacy. To the best of our knowledge, this work is the first to address this problem in a black-box scenario, where only…

Cryptography and Security · Computer Science 2022-12-12 Tim Kutta , Önder Askin , Martin Dunsche

In the highly interconnected realm of Internet of Things, exchange of sensitive information raises severe privacy concerns. The Laplace mechanism -- adding Laplace-distributed artificial noise to sensitive data -- is one of the widely used…

Cryptography and Security · Computer Science 2015-04-09 Fragkiskos Koufogiannis , Shuo Han , George J. Pappas

Artificial Intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive, for example in medical imaging. Privacy Enhancing Technologies (PETs), such as Differential Privacy (DP), aim…

We generalize a previous framework for designing utility-optimal differentially private (DP) mechanisms via graphs, where datasets are vertices in the graph and edges represent dataset neighborhood. The boundary set contains datasets where…

Data Structures and Algorithms · Computer Science 2022-03-30 Sahel Torkamani , Javad B. Ebrahimi , Parastoo Sadeghi , Rafael G. L. D'Oliveira , Muriel Medard

The widespread collection and sharing of location data, even in aggregated form, raises major privacy concerns. Previous studies used meta-classifier-based membership inference attacks~(MIAs) with multi-layer perceptrons~(MLPs) to estimate…

Cryptography and Security · Computer Science 2024-12-31 Yuhan Liu , Florent Guepin , Igor Shilov , Yves-Alexandre De Montjoye

We consider a multi-armed bandit setting with finitely many arms, in which each arm yields an $M$-dimensional vector reward upon selection. We assume that the reward of each dimension (a.k.a. {\em objective}) is generated independently of…

Machine Learning · Computer Science 2025-01-24 Zhirui Chen , P. N. Karthik , Yeow Meng Chee , Vincent Y. F. Tan

Many resource allocation problems can be formulated as an optimization problem whose constraints contain sensitive information about participating users. This paper concerns solving this kind of optimization problem in a distributed manner…

Optimization and Control · Mathematics 2016-11-17 Shuo Han , Ufuk Topcu , George J. Pappas