Online learning methods for networking

DOI10.1561/1300000050MaRDI QIDQ2799529zbMATH OpenOpenAlexFDO

Authors Cem Tekin, Mingyan Liu

Publication date 11 April 2016

Published in Foundations and Trends in Networking (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1561/1300000050

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to probability theory (60-02) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Online algorithms; streaming algorithms (68W27) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)

Recommendations

• Multi-Armed Bandits: Theory and Applications to Online Learning in Networks
• Optimal learning and experimentation in bandit problems.
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Introduction to multi-armed bandits
• Sequential learning and decision-making in wireless resource management

Cited in

(6)

• Differentially private and budget-limited bandit learning over matroids
• Sequential learning and decision-making in wireless resource management
• Multi-Armed Bandits: Theory and Applications to Online Learning in Networks
• Online learning of network bottlenecks via minimax paths
• An asymptotically optimal strategy for constrained multi-armed bandit problems
• Combining multiple strategies for multiarmed bandit problems and asymptotic optimality

This page was built for publication: Online learning methods for networking

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2799529)