ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1807.02290
26
6

Differentially Private Online Submodular Optimization

6 July 2018
Adrian Rivera Cardoso
Rachel Cummings
ArXiv (abs)PDFHTML
Abstract

In this paper we develop the first algorithms for online submodular minimization that preserve differential privacy under full information feedback and bandit feedback. A sequence of TTT submodular functions over a collection of nnn elements arrive online, and at each timestep the algorithm must choose a subset of [n][n][n] before seeing the function. The algorithm incurs a cost equal to the function evaluated on the chosen set, and seeks to choose a sequence of sets that achieves low expected regret. Our first result is in the full information setting, where the algorithm can observe the entire function after making its decision at each timestep. We give an algorithm in this setting that is ϵ\epsilonϵ-differentially private and achieves expected regret O~(n3/2Tϵ)\tilde{O}\left(\frac{n^{3/2}\sqrt{T}}{\epsilon}\right)O~(ϵn3/2T​​). This algorithm works by relaxing submodular function to a convex function using the Lovasz extension, and then simulating an algorithm for differentially private online convex optimization. Our second result is in the bandit setting, where the algorithm can only see the cost incurred by its chosen set, and does not have access to the entire function. This setting is significantly more challenging because the algorithm does not receive enough information to compute the Lovasz extension or its subgradients. Instead, we construct an unbiased estimate using a single-point estimation, and then simulate private online convex optimization using this estimate. Our algorithm using bandit feedback is ϵ\epsilonϵ-differentially private and achieves expected regret O~(n3/2T3/4ϵ)\tilde{O}\left(\frac{n^{3/2}T^{3/4}}{\epsilon}\right)O~(ϵn3/2T3/4​).

View on arXiv
Comments on this paper