Adaptive routing with end-to-end feedback: distributed learning and geometric approaches

DOI10.1145/1007352.1007367MaRDI QIDQ3580958zbMATH OpenOpenAlexFDO

Authors Baruch Awerbuch, Robert D. Kleinberg

Publication date 15 August 2010

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

Full work available at URL https://doi.org/10.1145/1007352.1007367

Mathematics Subject Classification ID

Network design and communication in computer systems (68M10) Programming involving graphs or networks (90C35)

Recommendations

• Online linear optimization and adaptive routing
• The on-line shortest path problem under partial monitoring
• The Shortest Path Problem Under Partial Monitoring
• Learning Theory
• An optimal adaptive routing algorithm

Cited in

(24)

• Randomized prediction of individual sequences
• Regret bounded by gradual variation for online convex optimization
• Online linear optimization and adaptive routing
• Efficient algorithms for online decision problems
• The on-line shortest path problem under partial monitoring
• Following the Perturbed Leader to Gamble at Multi-armed Bandits
• Approximating Wardrop equilibria with finitely many agents
• Management of Variable Data Streams in Networks
• scientific article; zbMATH DE number 3896627 (Why is no real title available?)
• Combinatorial bandits
• Sequential Shortest Path Interdiction with Incomplete Information
• Efficient online linear optimization with approximation algorithms
• Bandit convex optimization in non-stationary environments
• Learning in combinatorial optimization: what and how to explore
• Online learning of Nash equilibria in congestion games
• The Shortest Path Problem Under Partial Monitoring
• Small-Loss Bounds for Online Learning with Partial Information
• Multi-armed bandit problem with online clustering as side information
• Optimal and efficient algorithms for decentralized online convex optimization
• A unified analysis of nonstochastic delayed feedback for combinatorial semi-bandits, linear bandits, and MDPs
• Top-k combinatorial bandits with full-bandit feedback
• Convergence to equilibrium of no-regret dynamics in congestion games
• Adaptive routing with stale information
• Dynamic choice in a complex world

This page was built for publication: Adaptive routing with end-to-end feedback: distributed learning and geometric approaches

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3580958)