mlsanityData to 7 Oct 2026

Differentially Private High Dimensional Bandits

arXiv 2402.03737 ↗First posted 6 Feb 2024cs.LG cs.CR cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

We consider a high-dimensional stochastic contextual linear bandit problem when the parameter vector is s0-sparse and the decision maker is subject to privacy constraints under both central and local models of differential privacy. 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 θ. We prove minimax private lower bounds and establish privacy and utility guarantees for PrivateLASSO for the central model under standard assumptions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 47 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

19 of 47 references.

References · 19

  1. 2018Differentially Private Contextual Linear Banditscited by 82
  2. 2020Gamification of Pure Exploration for Linear Banditscited by 61
  3. 2020High-Dimensional Sparse Linear Banditscited by 61
  4. 2020Locally Differentially Private (Contextual) Bandits Learningcited by 52
  5. 2020Sparsity-Agnostic Lasso Banditcited by 44
  6. 2019Adaptive Exploration in Linear Contextual Banditcited by 43
  7. 2020Multi-Armed Bandits with Local Differential Privacycited by 37
  8. 2015Local, Private, Efficient Protocols for Succinct Histogramscited by 35
  9. 2021Generalized Linear Bandits with Local Differential Privacycited by 29
  10. 2013Private Matchings and Allocationscited by 23
  11. 2020Privacy-Preserving Dynamic Personalized Pricing with Demand Learningcited by 23
  12. 2021A Simple Unified Framework for High Dimensional Bandit Problemscited by 21
7 more
  1. 2022Differentially Private Stochastic Linear Bandits: (Almost) for Freecited by 19
  2. 2020Thresholded Lasso Banditcited by 16
  3. 2020The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Boundscited by 15
  4. 2015Private Approximations of the 2nd-Moment Matrix Using Existing Techniques in Linear Regressioncited by 8
  5. 2013Asymptotically Truthful Equilibrium Selection in Large Congestion Gamescited by 5
  6. 2020PAPRIKA: Private Online False Discovery Rate Controlcited by 3
  7. 2016The Possibilities and Limitations of Private Prediction Marketscited by 2

Built on by

Not cited yet.