FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits

• URL: http://arxiv.org/abs/2405.14038v3
• Date: Tue, 29 Oct 2024 05:30:08 GMT
• Title: FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits
• Authors: Sunrit Chakraborty, Saptarshi Roy, Debabrota Basu,
• Abstract summary: 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.
• Score: 8.908421753758475
• License:
• Abstract: High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems (e.g. personalized medicine), where high dimensional features (e.g. genomic data) on the users are available, but only a small subset of them are relevant. Motivated by data privacy concerns in these applications, we study the joint differentially private high dimensional sparse linear bandits, where both rewards and contexts are considered as private data. First, to quantify the cost of privacy, we derive a lower bound on the regret achievable in this setting. To further address the problem, we design a computationally efficient bandit algorithm, \textbf{F}orgetfu\textbf{L} \textbf{I}terative \textbf{P}rivate \textbf{HA}rd \textbf{T}hresholding (FLIPHAT). Along with doubling of episodes and episodic forgetting, FLIPHAT deploys a variant of Noisy Iterative Hard Thresholding (N-IHT) algorithm as a sparse linear regression oracle to ensure both privacy and regret-optimality. We show that FLIPHAT achieves optimal regret in terms of privacy parameters $\epsilon, \delta$, context dimension $d$, and time horizon $T$ up to a linear factor in model sparsity and logarithmic factor in $d$. We analyze the regret by providing a novel refined analysis of the estimation error of N-IHT, which is of parallel interest.

Related papers

• Near-Optimal Private Learning in Linear Contextual Bandits [61.39697409886124]
  We analyze the problem of private learning in generalized linear contextual bandits. Our results imply that joint privacy is almost "for free" in all the settings we consider.
  arXiv  Detail & Related papers  (2025-02-18T18:35:24Z)
• Differentially Private Kernelized Contextual Bandits [8.658538065693206]
  We consider the problem of contextual kernel bandits with contexts, where the underlying reward function belongs to a known Reproducing Kernel Hilbert Space (RKHS) We propose a novel algorithm that improves upon the state of the art and achieves an error rate of $mathcalOleft(sqrtfracgamma_TT + fracgamma_TT varepsilonright)$ after $T$ queries.
  arXiv  Detail & Related papers  (2025-01-13T04:05:19Z)
• Optimized Tradeoffs for Private Prediction with Majority Ensembling [59.99331405291337]
  We introduce the Data-dependent Randomized Response Majority (DaRRM) algorithm. DaRRM is parameterized by a data-dependent noise function $gamma$, and enables efficient utility optimization over the class of all private algorithms. 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)
• Differentially Private Best-Arm Identification [14.916947598339988]
  Best Arm Identification (BAI) problems are progressively used for data-sensitive applications. Motivated by the data privacy concerns invoked by these applications, we study the problem of BAI with fixed confidence in both the local and central models.
  arXiv  Detail & Related papers  (2024-06-10T16:02:48Z)
• Contextual Dynamic Pricing: Algorithms, Optimality, and Local Differential Privacy Constraints [10.057344315478709]
  We study the contextual dynamic pricing problem where a firm sells products to $T$ sequentially arriving consumers. We first show that the optimal regret upper bound is of order $sqrtdT$, up to a logarithmic factor. A key insight of our theoretical result is an intrinsic connection between dynamic pricing and the contextual multi-armed bandit problem.
  arXiv  Detail & Related papers  (2024-06-04T15:44:10Z)
• On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence [16.295693624977563]
  We study the problem of Best Arm Identification with fixed confidence under $epsilon$-global Differential Privacy. Our lower bound suggests the existence of two privacy regimes depending on the privacy budget. We propose AdaP-TT, an $epsilon$-global DP variant of the Top Two algorithm.
  arXiv  Detail & Related papers  (2023-09-05T13:07:25Z)
• On Differential Privacy and Adaptive Data Analysis with Bounded Space [76.10334958368618]
  We study the space complexity of the two related fields of differential privacy and adaptive data analysis. We show that there exists a problem P that requires exponentially more space to be solved efficiently with differential privacy. The line of work on adaptive data analysis focuses on understanding the number of samples needed for answering a sequence of adaptive queries.
  arXiv  Detail & Related papers  (2023-02-11T14:45:31Z)
• 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)
• Generalized Linear Bandits with Local Differential Privacy [4.922800530841394]
  Many applications such as personalized medicine and online advertising require the utilization of individual-specific information for effective learning. This motivates the introduction of local differential privacy (LDP), a stringent notion in privacy, to contextual bandits. In this paper, we design LDP algorithms for generalized linear bandits to achieve the same regret bound as in non-privacy settings.
  arXiv  Detail & Related papers  (2021-06-07T06:42:00Z)
• Learning with User-Level Privacy [61.62978104304273]
  We analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution. We derive an algorithm that privately answers a sequence of $K$ adaptively chosen queries with privacy cost proportional to $tau$, and apply it to solve the learning tasks we consider.
  arXiv  Detail & Related papers  (2021-02-23T18:25:13Z)
• Nearly Dimension-Independent Sparse Linear Bandit over Small Action Spaces via Best Subset Selection [71.9765117768556]
  We consider the contextual bandit problem under the high dimensional linear model. This setting finds essential applications such as personalized recommendation, online advertisement, and personalized medicine. We propose doubly growing epochs and estimating the parameter using the best subset selection method.
  arXiv  Detail & Related papers  (2020-09-04T04:10:39Z)

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.