English
Related papers

Related papers: Locally Differentially Private Thresholding Bandit…

200 papers

Privacy-preserving data analysis is a rising challenge in contemporary statistics, as the privacy guarantees of statistical methods are often achieved at the expense of accuracy. In this paper, we investigate the tradeoff between…

Machine Learning · Statistics 2020-11-11 T. Tony Cai , Yichen Wang , Linjun Zhang

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

We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender systems, the goal is to maximize the sum of the…

Machine Learning · Computer Science 2017-11-06 Pratik Gajane , Tanguy Urvoy , Emilie Kaufmann

Item mining, a fundamental task for collecting statistical data from users, has raised increasing privacy concerns. To address these concerns, local differential privacy (LDP) was proposed as a privacy-preserving technique. Existing LDP…

Cryptography and Security · Computer Science 2025-04-21 Yulian Mao , Qingqing Ye , Rong Du , Qi Wang , Kai Huang , Haibo Hu

Sensitive statistics are often collected across sets of users, with repeated collection of reports done over time. For example, trends in users' private preferences or software usage may be monitored via such reports. We study the…

Machine Learning · Computer Science 2020-07-28 Úlfar Erlingsson , Vitaly Feldman , Ilya Mironov , Ananth Raghunathan , Kunal Talwar , Abhradeep Thakurta

One of two independent stochastic processes (arms) are to be selected at each of n stages. The selection is sequential and depends on past observations as well as the prior information. Observations from arm i are independent given a…

Statistics Theory · Mathematics 2011-01-26 Yaming Yu

We identify fundamental tradeoffs between statistical utility and privacy under local models of privacy in which data is kept private even from the statistician, providing instance-specific bounds for private estimation and learning…

Statistics Theory · Mathematics 2020-10-01 John C. Duchi , Feng Ruan

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise…

Machine Learning · Computer Science 2025-08-22 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett

Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are…

Machine Learning · Computer Science 2021-03-29 Chris Waites , Rachel Cummings

We give an $(\varepsilon,\delta)$-differentially private algorithm for the multi-armed bandit (MAB) problem in the shuffle model with a distribution-dependent regret of $O\left(\left(\sum_{a\in [k]:\Delta_a>0}\frac{\log…

Machine Learning · Computer Science 2021-10-29 Jay Tenenbaum , Haim Kaplan , Yishay Mansour , Uri Stemmer

Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical trials, tuning hyper-parameters, and conducting user studies to name a few. Motivated by the data privacy…

Machine Learning · Statistics 2023-09-06 Achraf Azize , Marc Jourdan , Aymen Al Marjani , Debabrota Basu

While classical formulations of multi-armed bandit problems assume that each arm's reward is independent and stationary, real-world applications often involve non-stationary environments and interdependencies between arms. In particular,…

Machine Learning · Computer Science 2025-06-19 Ryoma Sato , Shinji Ito

In this paper, we study the problem of global reward maximization with only partial distributed feedback. This problem is motivated by several real-world applications (e.g., cellular network configuration, dynamic pricing, and policy…

Machine Learning · Computer Science 2024-03-22 Fengjiao Li , Xingyu Zhou , Bo Ji

Compressing the output of \epsilon-locally differentially private (LDP) randomizers naively leads to suboptimal utility. In this work, we demonstrate the benefits of using schemes that jointly compress and privatize the data using shared…

Cryptography and Security · Computer Science 2022-03-01 Abhin Shah , Wei-Ning Chen , Johannes Balle , Peter Kairouz , Lucas Theis

Local Differential Privacy (LDP) has been widely recognized as a powerful tool for providing a strong theoretical guarantee of data privacy to data contributors against an untrusted data collector. Under a typical LDP scheme, each data…

Cryptography and Security · Computer Science 2025-06-17 Ye Zheng , Shafizur Rahman Seeam , Yidan Hu , Rui Zhang , Yanchao Zhang

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP tasks. We propose a…

In this paper, we use differential privacy as a lens to examine online learning in both full and partial information settings. The differential privacy framework is, at heart, less about privacy and more about algorithmic stability, and…

Machine Learning · Computer Science 2019-10-30 Jacob Abernethy , Young Hun Jung , Chansoo Lee , Audra McMillan , Ambuj Tewari

This paper proposes a differentially private recursive least squares algorithm to estimate the parameter of autoregressive systems with exogenous inputs and multi-participants (MP-ARX systems) and protect each participant's sensitive…

Systems and Control · Electrical Eng. & Systems 2025-03-03 Jianwei Tan , Jimin Wang , Ji-Feng Zhang

Bandit algorithms are guaranteed to solve diverse sequential decision-making problems, provided that a sufficient exploration budget is available. However, learning from scratch is often too costly for personalization tasks where a single…

Machine Learning · Computer Science 2025-08-08 Newton Mwai , Emil Carlsson , Fredrik D. Johansson

In this paper, we study Combinatorial Semi-Bandits (CSB) that is an extension of classic Multi-Armed Bandits (MAB) under Differential Privacy (DP) and stronger Local Differential Privacy (LDP) setting. Since the server receives more…

Machine Learning · Computer Science 2020-07-06 Xiaoyu Chen , Kai Zheng , Zixin Zhou , Yunchang Yang , Wei Chen , Liwei Wang