Near-Optimal Private Learning in Linear Contextual Bandits

• URL: http://arxiv.org/abs/2502.13115v1
• Date: Tue, 18 Feb 2025 18:35:24 GMT
• Title: Near-Optimal Private Learning in Linear Contextual Bandits
• Authors: Fan Chen, Jiachun Li, Alexander Rakhlin, David Simchi-Levi,
• Abstract summary: 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.
• Score: 61.39697409886124
• License:
• Abstract: We analyze the problem of private learning in generalized linear contextual bandits. Our approach is based on a novel method of re-weighted regression, yielding an efficient algorithm with regret of order $\sqrt{T}+\frac{1}{\alpha}$ and $\sqrt{T}/\alpha$ in the joint and local model of $\alpha$-privacy, respectively. Further, we provide near-optimal private procedures that achieve dimension-independent rates in private linear models and linear contextual bandits. In particular, our results imply that joint privacy is almost "for free" in all the settings we consider, partially addressing the open problem posed by Azize and Basu (2024).

Related papers

• Smoothed Normalization for Efficient Distributed Private Optimization [54.197255548244705]
  Federated learning enables machine learning models with privacy of participants. There is no differentially private distributed method for training, non-feedback problems. We introduce a new distributed algorithm $alpha$-$sf NormEC$ with provable convergence guarantees.
  arXiv  Detail & Related papers  (2025-02-19T07:10:32Z)
• 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)
• 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)
• On the Optimal Regret of Locally Private Linear Contextual Bandit [18.300225068036642]
  We show that it is possible to achieve an $tilde O(sqrtT)$ regret upper bound for locally private linear contextual bandit. Our solution relies on several new algorithmic and analytical ideas.
  arXiv  Detail & Related papers  (2024-04-15T02:00:24Z)
• Differentially Private High Dimensional Bandits [1.3597551064547502]
  We present PrivateLASSO, a differentially private LASSO bandit algorithm. PrivateLASSO is based on two sub-routines: (i) a sparse hard-thresholding-based privacy mechanism and (ii) an episodic thresholding rule for identifying the support of the parameter $theta$.
  arXiv  Detail & Related papers  (2024-02-06T06:10:46Z)
• The Challenge of Differentially Private Screening Rules [32.18582226044492]
  We develop the first differentially private screening rule for linear and logistic regression. In doing so, we discover difficulties in the task of making a useful private screening rule due to the amount of noise added to ensure privacy.
  arXiv  Detail & Related papers  (2023-03-18T01:45:34Z)
• 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)
• Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling [49.43288037509783]
  We show that random shuffling amplifies differential privacy guarantees of locally randomized data. Our result is based on a new approach that is simpler than previous work and extends to approximate differential privacy with nearly the same guarantees.
  arXiv  Detail & Related papers  (2020-12-23T17:07:26Z)
• Locally Differentially Private (Contextual) Bandits Learning [55.63825598391525]
  We study locally differentially private (LDP) bandits learning in this paper. We propose simple black-box reduction frameworks that can solve a large family of context-free bandits learning problems with LDP guarantee.
  arXiv  Detail & Related papers  (2020-06-01T04:02:00Z)

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.