Bandits with switching costs

DOI10.1145/2591796.2591868zbMath1315.68207arXiv1310.2997OpenAlexW2109690147MaRDI QIDQ5259581

Jian Ding, Ofer Dekel, Yuval Peres, Tomer Koren

Publication date: 26 June 2015

Published in: Proceedings of the forty-sixth annual ACM symposium on Theory of computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1310.2997

zbMATH Keywords

online learninglower boundsswitching costsmulti-armed bandit

Mathematics Subject Classification ID

Sums of independent random variables; random walks (60G50) Learning and adaptive systems in artificial intelligence (68T05) Rationality and learning in game theory (91A26) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17) Randomized algorithms (68W20) Online algorithms; streaming algorithms (68W27)

Related Items (3)

Constrained no-regret learning ⋮ Chasing Ghosts: Competing with Stateful Policies ⋮ Online Learning over a Finite Action Set with Limited Switching

Uses Software

• SuLQ

Cites Work

• Unnamed Item
• Unnamed Item
• Efficient algorithms for privately releasing marginals via convex relaxations
• The Geometry of Differential Privacy: The Small Database and Approximate Cases
• Faster Algorithms for Privately Releasing Marginals
• Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
• Privately Releasing Conjunctions and the Statistical Query Barrier
• On the geometry of differential privacy
• Interactive privacy via the median mechanism
• The price of privately releasing contingency tables and the spectra of random matrices with correlated rows
• Lower Bounds in Differential Privacy
• Iterative Constructions and Private Data Release
• Characterizing the sample complexity of private learners
• Faster private release of marginals on small databases
• Bounds on the Sample Complexity for Private Learning and Private Data Release
• Differential Privacy and the Fat-Shattering Dimension of Linear Queries
• Our Data, Ourselves: Privacy Via Distributed Noise Generation
• New Efficient Attacks on Statistical Disclosure Control Mechanisms
• Collusion-secure fingerprinting for digital data
• On the complexity of differentially private data release
• Advances in Cryptology – CRYPTO 2004
• Answering n _{2+o(1)} counting queries with differential privacy is hard
• Theory of Cryptography

This page was built for publication: Bandits with switching costs