中文
相关论文

相关论文: On the Complexity of Differentially Private Best-A…

200 篇论文

Differential privacy (DP) has become the de facto standard for protecting sensitive data, providing strong guarantees that published statistics or models reveal limited information about any individual. However, privacy noise and restricted…

数据库 · 计算机科学 2026-05-25 Mariia Vologdin , Yuchao Tao , Amir Gilad

We study mean estimation for Gaussian distributions under \textit{personalized differential privacy} (PDP), where each record has its own privacy budget. PDP is commonly considered in two variants: \textit{bounded} and \textit{unbounded}…

数据结构与算法 · 计算机科学 2026-01-23 Wei Dong , Li Ge

This paper targets a variant of the stochastic multi-armed bandit problem called good arm identification (GAI). GAI is a pure-exploration bandit problem with the goal to output as many good arms using as few samples as possible, where a…

机器学习 · 计算机科学 2024-02-19 Yun-Da Tsai , Tzu-Hsien Tsai , Shou-De Lin

In good arm identification (GAI), the goal is to identify one arm whose average performance exceeds a given threshold, referred to as a good arm, if it exists. Few works have studied GAI in the fixed-budget setting when the sampling budget…

机器学习 · 统计学 2026-01-08 Marc Jourdan , Andrée Delahaye-Duriez , Clémence Réda

Fingerprinting arguments, first introduced by Bun, Ullman, and Vadhan (STOC 2014), are the most widely used method for establishing lower bounds on the sample complexity or error of approximately differentially private (DP) algorithms.…

密码学与安全 · 计算机科学 2024-07-08 Naty Peter , Eliad Tsfadia , Jonathan Ullman

This paper investigates the best arm identification (BAI) problem in stochastic multi-armed bandits in the fixed confidence setting. The general class of the exponential family of bandits is considered. The existing algorithms for the…

机器学习 · 统计学 2023-06-26 Arpan Mukherjee , Ali Tajer

In this paper, we study the stochastic linear bandit problem under the additional requirements of differential privacy, robustness and batched observations. In particular, we assume an adversary randomly chooses a constant fraction of the…

机器学习 · 计算机科学 2023-04-25 Vasileios Charisopoulos , Hossein Esfandiari , Vahab Mirrokni

Developing robust and effective artificial intelligence (AI) models in medicine requires access to large amounts of patient data. The use of AI models solely trained on large multi-institutional datasets can help with this, yet the…

We study the application of differential privacy in hyper-parameter tuning, a crucial process in machine learning involving selecting the best hyper-parameter from several candidates. Unlike many private learning algorithms, including the…

机器学习 · 计算机科学 2025-08-26 Zihang Xiang , Tianhao Wang , Chenglong Wang , Di Wang

The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between any two neighboring databases. However, traditional differentially private mechanisms tend to produce…

密码学与安全 · 计算机科学 2023-11-07 Kai Zhang , Yanjun Zhang , Ruoxi Sun , Pei-Wei Tsai , Muneeb Ul Hassan , Xin Yuan , Minhui Xue , Jinjun Chen

The best-arm identification (BAI) problem is one of the most fundamental problems in interactive machine learning, which has two flavors: the fixed-budget setting (FB) and the fixed-confidence setting (FC). For $K$-armed bandits with the…

In this paper, we study a best arm identification problem with dual objects. In addition to the classic reward, each arm is associated with a cost distribution and the goal is to identify the largest reward arm using the minimum expected…

机器学习 · 计算机科学 2024-07-02 Kellen Kanarios , Qining Zhang , Lei Ying

Concern about how to aggregate sensitive user data without compromising individual privacy is a major barrier to greater availability of data. The model of differential privacy has emerged as an accepted model to release sensitive…

数据库 · 计算机科学 2017-10-03 Graham Cormode , Tejas Kulkarni , Divesh Srivastava

In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy by adding noise at…

机器学习 · 统计学 2021-10-28 Tejas Kulkarni , Joonas Jälkö , Samuel Kaski , Antti Honkela

The Alternating Direction Method of Multipliers (ADMM) and its distributed version have been widely used in machine learning. In the iterations of ADMM, model updates using local private data and model exchanges among agents impose critical…

机器学习 · 计算机科学 2020-08-12 Jiahao Ding , Jingyi Wang , Guannan Liang , Jinbo Bi , Miao Pan

We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or…

密码学与安全 · 计算机科学 2026-02-09 Tim Kutta , Martin Dunsche , Yu Wei , Vassilis Zikas

We study the fixed-confidence best arm identification (BAI) problem within the multi-armed bandit (MAB) framework under the Entropic Value-at-Risk (EVaR) criterion. Our analysis considers a nonparametric setting, allowing for general reward…

机器学习 · 计算机科学 2025-10-07 Mehrasa Ahmadipour , Aurélien Garivier

Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning. While many TD learning methods have been developed in recent years, little attention has been paid to preserving privacy and most of…

机器学习 · 计算机科学 2022-01-26 Canzhe Zhao , Yanjie Ze , Jing Dong , Baoxiang Wang , Shuai Li

Differential Privacy (DP) has become a gold standard in privacy-preserving data analysis. While it provides one of the most rigorous notions of privacy, there are many settings where its applicability is limited. Our main contribution is in…

密码学与安全 · 计算机科学 2021-10-20 Aman Bansal , Rahul Chunduru , Deepesh Data , Manoj Prabhakaran

Differential privacy is a privacy measure based on the difficulty of discriminating between similar input data. In differential privacy analysis, similar data usually implies that their distance does not exceed a predetermined threshold.…

最优化与控制 · 数学 2021-06-25 Genki Sugiura , Kaito Ito , Kenji Kashima