Differentially private and budget-limited bandit learning over matroids

DOI10.1287/IJOC.2019.0903MaRDI QIDQ3386800zbMATH OpenOpenAlexFDO

Authors Kai Han, Yuntian He, Alex X. Liu, Shaojie Tang, He Huang

Publication date 7 January 2021

Published in INFORMS Journal on Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/ijoc.2019.0903

zbMATH Keywords

budgetmatroidmulti-armed bandit

Mathematics Subject Classification ID

Combinatorial aspects of matroids and geometric lattices (05B35) Sequential statistical analysis (62L10) Optimal stopping in statistics (62L15) Privacy of data (68P27) Learning and adaptive systems in artificial intelligence (68T05) Combinatorial optimization (90C27)

Recommendations

• Approximation algorithms for budgeted learning problems
• Bandits with knapsacks
• Distributed online bandit linear regressions with differential privacy
• Budgeted multi-armed bandit in continuous action space
• Corrupt bandits for preserving local privacy

Cites work

• Combinatorial Optimization with Rational Objective Functions
• Encyclopedia of Optimization
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 5717961 (Why is no real title available?)
• scientific article; zbMATH DE number 5873618 (Why is no real title available?)
• Introduction to algorithms.
• Maximizing a monotone submodular function subject to a matroid constraint
• Measure, probability, and mathematical finance. A problem-oriented approach
• Online learning methods for networking
• Probability and Computing
• Probability and random processes.
• Probability Inequalities for Sums of Bounded Random Variables
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Stochastic Online Shortest Path Routing: The Value of Feedback
• The algorithmic foundations of differential privacy

Cited in

(5)

• Secure best arm identification in multi-armed bandits
• Budgeted multi-armed bandit in continuous action space
• Corrupt bandits for preserving local privacy
• SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits
• Distributed online bandit linear regressions with differential privacy

Describes a project that uses

Uses Software

• CPLEX

This page was built for publication: Differentially private and budget-limited bandit learning over matroids

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3386800)