Differentially Private Kernelized Contextual Bandits
Not on the map. Why?
Abstract (arXiv)
We consider the problem of contextual kernel bandits with stochastic contexts, where the underlying reward function belongs to a known Reproducing Kernel Hilbert Space (RKHS). We study this problem under the additional constraint of joint differential privacy, where the agents needs to ensure that the sequence of query points is differentially private with respect to both the sequence of contexts and rewards. We propose a novel algorithm that improves upon the state of the art and achieves an error rate of Oleft(√fracγTT + fracγTT varepsilonright) after T queries for a large class of kernel families, where γT represents the effective dimensionality of the kernel and varepsilon > 0 is the privacy parameter. Our results are based on a novel estimator for the reward function that simultaneously enjoys high utility along with a low-sensitivity to observed rewards and contexts, which is crucial to obtain an order optimal learning performance with improved dependence on the privacy parameter.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 13 Jan 2025.
Builds on
27 of 32 references.
References · 27
- 2017On Kernelized Multi-armed Banditscited by 348
- 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
- 2020On Information Gain and Regret Bounds in Gaussian Process Banditscited by 156
- 2020Differentially-Private Federated Linear Banditscited by 83
- 2017Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimizationcited by 77
- 2021Gaussian Process Bandit Optimization with Few Batchescited by 57
- 2020Locally Differentially Private (Contextual) Bandits Learningcited by 52
- 2021Optimal Order Simple Regret for Gaussian Process Banditscited by 52
- 2020A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performancecited by 38
- 2021Differentially Private Federated Bayesian Optimization with Distributed Explorationcited by 32
- 2021Generalized Linear Bandits with Local Differential Privacycited by 29
- 2020Practical Hilbert space approximate Bayesian Gaussian processes for probabilistic programmingcited by 28
15 more
- 2022When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Banditscited by 28
- 2023On the Sublinear Regret of GP-UCBcited by 25
- 2020Local Differential Privacy for Bayesian Optimizationcited by 19
- 2022Differentially Private Stochastic Linear Bandits: (Almost) for Freecited by 19
- 2022Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithmscited by 19
- 2022Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learningcited by 18
- 2021Privacy Amplification via Shuffling for Linear Contextual Banditscited by 17
- 2020Multi-Scale Zero-Order Optimization of Smooth Functions in an RKHScited by 16
- 2020Private Outsourced Bayesian Optimizationcited by 15
- 2023On Differentially Private Federated Linear Contextual Banditscited by 14
- 2022Distributed Contextual Linear Bandits with Minimax Optimal Communication Costcited by 13
- 2015Differentially Private Bayesian Optimizationcited by 12
- 2018Online learning with kernel lossescited by 12
- 2023Federated Linear Contextual Bandits with User-level Differential Privacycited by 12
- 2021No-Regret Algorithms for Private Gaussian Process Bandit Optimizationcited by 11
Built on by
Citing papers per year: 2025: 3.
3 papers.