English
Related papers

Related papers: Concentrated Differential Privacy for Bandits

200 papers

In this work, we study sequential choice bandits with feedback. We propose bandit algorithms for a platform that personalizes users' experience to maximize its rewards. For each action directed to a given user, the platform is given a…

Machine Learning · Statistics 2021-01-06 Anshuka Rangi , Massimo Franceschetti , Long Tran-Thanh

Label differential privacy (DP) is designed for learning problems involving private labels and public features. While various methods have been proposed for learning under label DP, the theoretical limits remain largely unexplored. In this…

Machine Learning · Computer Science 2025-03-04 Puning Zhao , Chuan Ma , Li Shen , Shaowei Wang , Rongfei Fan

With the growing demand for personalized assortment recommendations, concerns over data privacy have intensified, highlighting the urgent need for effective privacy-preserving strategies. This paper presents a novel framework for…

Machine Learning · Statistics 2024-10-31 Young Hyun Cho , Will Wei Sun

Differential Privacy (DP) was originally developed to protect privacy. However, it has recently been utilized to secure machine learning (ML) models from poisoning attacks, with DP-SGD receiving substantial attention. Nevertheless, a…

Cryptography and Security · Computer Science 2023-11-13 Fereshteh Razmi , Jian Lou , Li Xiong

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Machine Learning · Computer Science 2023-07-25 Ayush Sekhari , Karthik Sridharan , Wen Sun , Runzhe Wu

Contextual multi-armed bandits (CMAB) have been widely used for learning to filter and prioritize information according to a user's interest. In this work, we analyze top-K ranking under the CMAB framework where the top-K arms are chosen…

Machine Learning · Computer Science 2022-01-31 Michael Rawson , Jade Freeman

Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy.…

Machine Learning · Computer Science 2019-10-29 Eugene Bagdasaryan , Vitaly Shmatikov

Upper Confidence Bound (UCB) algorithms are a widely-used class of sequential algorithms for the $K$-armed bandit problem. Despite extensive research over the past decades aimed at understanding their asymptotic and (near) minimax…

Statistics Theory · Mathematics 2024-12-10 Qiyang Han , Koulik Khamaru , Cun-Hui Zhang

Differential privacy (DP) is a formal notion for quantifying the privacy loss of algorithms. Algorithms in the central model of DP achieve high accuracy but make the strongest trust assumptions whereas those in the local DP model make the…

Cryptography and Security · Computer Science 2021-06-09 Badih Ghazi , Ravi Kumar , Pasin Manurangsi , Rasmus Pagh

Conservative Contextual Bandits (CCBs) address safety in sequential decision making by requiring that an agent's policy, along with minimizing regret, also satisfies a safety constraint: the performance is not worse than a baseline policy…

Machine Learning · Computer Science 2024-12-10 Rohan Deb , Mohammad Ghavamzadeh , Arindam Banerjee

Achieving differential privacy (DP) guarantees in fully decentralized machine learning is challenging due to the absence of a central aggregator and varying trust assumptions among nodes. We present a framework for DP analysis of…

Machine Learning · Computer Science 2026-02-06 Antti Koskela , Tejas Kulkarni

Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision…

Machine Learning · Computer Science 2022-03-22 Xingyu Zhou

Bandit algorithms have become a reference solution for interactive recommendation. However, as such algorithms directly interact with users for improved recommendations, serious privacy concerns have been raised regarding its practical use.…

Machine Learning · Computer Science 2022-09-01 Huazheng Wang , David Zhao , Hongning Wang

We introduce a Multi-User Contextual Cascading Bandit model, a new combinatorial bandit framework that captures realistic online advertising scenarios where multiple users interact with sequentially displayed items simultaneously. Unlike…

Machine Learning · Computer Science 2025-08-26 Jiho Park , Huiwen Jia

Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…

Cryptography and Security · Computer Science 2025-06-25 Saeed Mahloujifar , Chuan Guo , G. Edward Suh , Kamalika Chaudhuri

The remarkable proliferation of deep learning across various industries has underscored the importance of data privacy and security in AI pipelines. As the evolution of sophisticated Membership Inference Attacks (MIAs) threatens the secrecy…

Cryptography and Security · Computer Science 2023-06-06 Eugenio Lomurno , Alberto Archetti , Francesca Ausonio , Matteo Matteucci

The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge. We propose a multi-armed bandit framework for matching incentives to users, whose…

Machine Learning · Computer Science 2018-07-09 Tanner Fiez , Shreyas Sekar , Liyuan Zheng , Lillian J. Ratliff

The causal bandit problem seeks to identify, through sequential experimentation, an intervention that maximizes the expected reward in a causal system modeled by a directed acyclic graph (DAG). Existing methods typically assume that the…

Machine Learning · Computer Science 2026-04-07 Yijia Zhao , Qing Zhou

In the past decade analysis of big data has proven to be extremely valuable in many contexts. Local Differential Privacy (LDP) is a state-of-the-art approach which allows statistical computations while protecting each individual user's…

Cryptography and Security · Computer Science 2019-07-30 Björn Bebensee

Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a…

Machine Learning · Computer Science 2021-01-13 Milad Nasr , Shuang Song , Abhradeep Thakurta , Nicolas Papernot , Nicholas Carlini