English
Related papers

Related papers: Local Differential Privacy for Regret Minimization…

200 papers

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

Cryptography and Security · Computer Science 2022-04-28 Zhigang Lu , Hassan Jameel Asghar , Mohamed Ali Kaafar , Darren Webb , Peter Dickinson

Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…

Cryptography and Security · Computer Science 2024-12-17 Bo Jiang , Wanrong Zhang , Donghang Lu , Jian Du , Sagar Sharma , Qiang Yan

Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the…

Machine Learning · Computer Science 2022-04-21 Jiafan He , Dongruo Zhou , Quanquan Gu

Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…

Machine Learning · Computer Science 2023-05-25 Geon Heo , Junseok Seo , Steven Euijong Whang

We consider online reinforcement learning in episodic Markov decision process (MDP) with unknown transition function and stochastic rewards drawn from some fixed but unknown distribution. The learner aims to learn the optimal policy and…

Machine Learning · Computer Science 2024-03-12 Vincent Leon , S. Rasoul Etesami

State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered…

Machine Learning · Computer Science 2019-11-01 Yonathan Efroni , Nadav Merlis , Mohammad Ghavamzadeh , Shie Mannor

Local differential privacy (LDP), a technique applying unbiased statistical estimations instead of real data, is often adopted in data collection. In particular, this technique is used with frequency oracles (FO) because it can protect each…

Cryptography and Security · Computer Science 2022-03-29 Dan Zhao , Suyun Zhao , Ruixuan Liu , Cuiping Li , Wenjuan Liang , Hong Chen

The growing number of applications of Reinforcement Learning (RL) in real-world domains has led to the development of privacy-preserving techniques due to the inherently sensitive nature of data. Most existing works focus on differential…

Machine Learning · Computer Science 2021-09-20 Alberto Jesu , Victor-Alexandru Darvariu , Alessandro Staffolani , Rebecca Montanari , Mirco Musolesi

Metric Differential Privacy (mDP) extends the concept of Differential Privacy (DP) to serve as a new paradigm of data perturbation. It is designed to protect secret data represented in general metric space, such as text data encoded as word…

Artificial Intelligence · Computer Science 2024-05-10 Chenxi Qiu

Local Differential Privacy (LDP) provides provable privacy protection for data collection without the assumption of the trusted data server. In the real-world scenario, different data have different privacy requirements due to the distinct…

Cryptography and Security · Computer Science 2020-02-25 Xiaolan Gu , Ming Li , Li Xiong , Yang Cao

We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations…

Machine Learning · Computer Science 2013-03-19 Odalric-Ambrym Maillard , Phuong Nguyen , Ronald Ortner , Daniil Ryabko

We initiate an investigation of node differential privacy for graphs in the local model of private data analysis. In our model, dubbed LNDP*, each node sees its own edge list and releases the output of a local randomizer on this input.…

Data Structures and Algorithms · Computer Science 2026-04-03 Sofya Raskhodnikova , Adam Smith , Connor Wagaman , Anatoly Zavyalov

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…

Machine Learning · Computer Science 2011-02-18 Kamalika Chaudhuri , Claire Monteleoni , Anand D. Sarwate

Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the…

Machine Learning · Computer Science 2024-02-22 Karima Makhlouf , Heber H. Arcolezi , Sami Zhioua , Ghassen Ben Brahim , Catuscia Palamidessi

This paper addresses the challenge of balancing learner data privacy with the use of data in learning analytics (LA) by proposing a novel framework by applying Differential Privacy (DP). The need for more robust privacy protection keeps…

Cryptography and Security · Computer Science 2025-01-06 Qinyi Liu , Ronas Shakya , Mohammad Khalil , Jelena Jovanovic

We study contextual dynamic pricing problems where a firm sells products to $T$ sequentially-arriving consumers, behaving according to an unknown demand model. The firm aims to minimize its regret over a clairvoyant that knows the model in…

Machine Learning · Computer Science 2025-04-07 Zifeng Zhao , Feiyu Jiang , Yi Yu

A large variety of real-world Reinforcement Learning (RL) tasks is characterized by a complex and heterogeneous structure that makes end-to-end (or flat) approaches hardly applicable or even infeasible. Hierarchical Reinforcement Learning…

Machine Learning · Computer Science 2023-05-12 Gianluca Drappo , Alberto Maria Metelli , Marcello Restelli

In order to make good decision under uncertainty an agent must learn from observations. To do so, two of the most common frameworks are Contextual Bandits and Markov Decision Processes (MDPs). In this paper, we study whether there exist…

Machine Learning · Computer Science 2019-11-05 Andrea Zanette , Emma Brunskill

We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the POMDP with a known environment in terms of the average reward over…

Machine Learning · Computer Science 2022-07-19 Yi Xiong , Ningyuan Chen , Xuefeng Gao , Xiang Zhou

In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development. Differential privacy (DP) has emerged as one canonical…

Machine Learning · Computer Science 2022-11-15 Zachary Izzo , Jinsung Yoon , Sercan O. Arik , James Zou