Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits

• URL: http://arxiv.org/abs/2602.00417v1
• Date: Sat, 31 Jan 2026 00:15:20 GMT
• Title: Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
• Authors: Sahasrajit Sarmasarkar,
• Abstract summary: We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy.<n>For adversarial contexts, we provide a joint-DP algorithm with $tildeO(dsqrtT/sqrtvarepsilon)$ regret.
• Score: 0.8122270502556375
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. While prior work on private contextual bandits has been restricted to linear reward models -- which admit closed-form estimators -- generalized linear models (GLMs) pose fundamental new challenges: no closed-form estimator exists, requiring private convex optimization; privacy must be tracked across multiple evolving design matrices; and optimization error must be explicitly incorporated into regret analysis. We address these challenges under two privacy models and context settings. For stochastic contexts, we design a shuffle-DP algorithm achieving $\tilde{O}(d^{3/2}\sqrt{T}/\sqrt{\varepsilon})$ regret. For adversarial contexts, we provide a joint-DP algorithm with $\tilde{O}(d\sqrt{T}/\sqrt{\varepsilon})$ regret -- matching the non-private rate up to a $1/\sqrt{\varepsilon}$ factor. Both algorithms remove dependence on the instance-specific parameter $κ$ (which can be exponential in dimension) from the dominant $\sqrt{T}$ term. Unlike prior work on locally private GLM bandits, our methods require no spectral assumptions on the context distribution beyond $\ell_2$ boundedness.

Related papers

• Tight Differentially Private PCA via Matrix Coherence [12.864472925970242]
  We show that a simple and efficient algorithm -- based on singular value decomposition and standard perturbation mechanisms -- returns a private rank-$r$ approximation.<n>Our estimator outperforms the state of the art -- significantly so in some regimes.<n>We conjecture that similar behavior holds for other structured models, including planted problems in graphs.
  arXiv  Detail & Related papers  (2025-10-30T16:47:26Z)
• Differential Privacy in Kernelized Contextual Bandits via Random Projections [8.658538065693206]
  We consider the problem of contextual kernel bandits with contexts.<n>The underlying reward function belongs to a known Reproducing Kernel Hilbert Space.<n>We propose a novel algorithm that achieves the state-of-the-art cumulative regret of $widetildemathcalO(sqrtgamma_TT+fracgamma_Tvarepsilon_mathrmDP)$
  arXiv  Detail & Related papers  (2025-07-18T03:54:49Z)
• Smoothed Normalization for Efficient Distributed Private Optimization [54.197255548244705]
  Federated learning enables machine learning models with privacy of participants.<n>There is no differentially private distributed method for training, non-feedback problems.<n>We introduce a new distributed algorithm $alpha$-$sf NormEC$ with provable convergence guarantees.
  arXiv  Detail & Related papers  (2025-02-19T07:10:32Z)
• Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression [66.93988594607842]
  Under privacy constraints, the complexity of private linear regression is emphnot captured by the usual covariance matrix.<n>We introduce an Information-Weighted Regression method that attains the optimal rates.<n> Notably, our results demonstrate that joint privacy comes at almost no additional cost.
  arXiv  Detail & Related papers  (2025-02-18T18:35:24Z)
• Optimized Tradeoffs for Private Prediction with Majority Ensembling [59.99331405291337]
  We introduce the Data-dependent Randomized Response Majority (DaRRM) algorithm.<n>DaRRM is parameterized by a data-dependent noise function $gamma$, and enables efficient utility optimization over the class of all private algorithms.<n>We show that DaRRM provably enjoys a privacy gain of a factor of 2 over common baselines, with fixed utility.
  arXiv  Detail & Related papers  (2024-11-27T00:48:48Z)
• FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits [8.908421753758475]
  High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems. Motivated by data privacy concerns, we study the joint differentially private high dimensional sparse linear bandits. We show that FLIPHAT achieves optimal regret in terms of privacy parameters.
  arXiv  Detail & Related papers  (2024-05-22T22:19:12Z)
• Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems [61.85150061213987]
  We study the generalized low-rank matrix bandit problem, proposed in citelu2021low under the Generalized Linear Model (GLM) framework. To overcome the computational infeasibility and theoretical restrain of existing algorithms, we first propose the G-ESTT framework. We show that G-ESTT can achieve the $tildeO(sqrt(d_1+d_2)3/2Mr3/2T)$ bound of regret while G-ESTS can achineve the $tildeO
  arXiv  Detail & Related papers  (2024-01-14T14:14:19Z)
• Private Online Prediction from Experts: Separations and Faster Rates [74.52487417350221]
  Online prediction from experts is a fundamental problem in machine learning and several works have studied this problem under privacy constraints. We propose and analyze new algorithms for this problem that improve over the regret bounds of the best existing algorithms for non-adaptive adversaries.
  arXiv  Detail & Related papers  (2022-10-24T18:40:19Z)
• Non-Euclidean Differentially Private Stochastic Convex Optimization [15.302167005107135]
  We show that noisy gradient descent (SGD) algorithms attain the optimal excess risk in low-dimensional regimes. Our work draws upon concepts from the geometry of normed spaces, such as the notions of regularity, uniform convexity, and uniform smoothness.
  arXiv  Detail & Related papers  (2021-03-01T19:48:44Z)
• Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds [72.63031036770425]
  We propose differentially private (DP) algorithms for bound non-dimensional optimization. We demonstrate two popular deep learning methods on the empirical advantages over standard gradient methods.
  arXiv  Detail & Related papers  (2020-06-24T06:01:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.